YouTube2Text

VIBE CODING FULL COURSE: Gemini 3.1 + Antigravity (6 Hrs) — Transcript

by Nick Saraev · 86,707 words · 4,785 segments · language en · Watch on YouTube

Full transcript

  1. 0:00Hey, welcome to the definitive course on vibe  coding for beginners. I use anti-gravity,
  2. 0:04Gemini 3.1 Pro, and Claude Code in my life every  day to manage a business that does over $4 million
  3. 0:09a year in profit. I also teach around 2,000 people  how to use technologies just like this to improve
  4. 0:14their lives, both personal and business. So, the  way this course is going to work is it'll start by
  5. 0:18teaching you guys how to set up anti-gravity,  Gemini, and then Claude Code in a simple
  6. 0:22development environment. And then we're going to  jump right into the building. And we'll start with
  7. 0:26simple portfolio sites before working our way  all the way up to full-fledged SAS apps with
  8. 0:30authentication, databases, and so on and so forth.  At every step along the way, I'm going to pause
  9. 0:35and then show you guys some of the principles  behind what I just built. And my recommendation
  10. 0:38is if you want to get the most out of this course,  you'd actually build alongside me. Okay, so no
  11. 0:42fluff. Here's what we're going to cover. We'll  start with the simple toolkit. So anti-gravity,
  12. 0:46Gemini 3.1 Pro, and Claude Code. I'll give  you guys the best development environment
  13. 0:49available in probably around 15 minutes. Then  we'll build your first vibecoded product,
  14. 0:53which in our case is going to be a personal  site designed with anti-gravity and Gemini.
  15. 0:56You'll have this live on the internet, including  deployment in about 15 minutes. After that,
  16. 1:00I'll pause to talk authentication and security cuz  I think it's one thing to build simple portfolio
  17. 1:04sites and stuff, but if you wanted to push that  out to a fullyfledged app with authentication,
  18. 1:08databases, and a back end, a big issue in vibe  coding is security, and I want to make sure
  19. 1:12that we cover at least the 8020 of that. Then  we'll build another product, which will be a
  20. 1:15client-f facing dashboard with authentication, a  database, and a very clean UI. And at that point,
  21. 1:19since we'll have gotten our hands dirty, we  can then cover foundational concepts behind
  22. 1:22modern software applications, including hosting,  databases, the major software design patterns,
  23. 1:28versioning and GitHub repositories, the major  frameworks currently available, then also how to
  24. 1:32use agents to vibe code all this stuff way faster.  I'm then going to give you a design specific deep
  25. 1:36dive, which is how to go from a rough idea to a  polished professional design and anti-gravity.
  26. 1:40Then we'll build our next product, which will be  a lead generation SAS app that scrapes, enriches,
  27. 1:44and then cues up the sending of fully automatic  emails. This is an actual system I use production.
  28. 1:48After that, we'll do an AI based SAS app that  uses AI to generate thumbnails. It's actually
  29. 1:52really similar to the system that I used to create  the thumbnail for the video you're watching right
  30. 1:55now. So, pretty meta. Once we're done with that,  I'm going to teach you guys some debugging and
  31. 1:58iteration techniques. You guys will probably have  seen me do a lot of this and hopefully have done
  32. 2:02a lot of it yourselves by now. But, I'm going  to give you guys a simple framework that you
  33. 2:05could use to steer back Gemini and then claude  code anytime it starts veering outside of your
  34. 2:09uh recommendations. And then finally, we'll build  a content automation SAS app that repurposes a
  35. 2:14single piece of content across multiple platforms.  That's another system that I actually use. Before
  36. 2:18we wrap up, we'll talk about the economics of  vibe coding, which is how to price, package,
  37. 2:22and then sell what you build. And that's important  because I find a lot of people watching this are
  38. 2:25probably going to be doing so not just for their  own hobbies, but for financial reasons. We want to
  39. 2:29make money with the things that we build. Okay, so  I care a lot about making money with this stuff.
  40. 2:33I want to show you guys how to do that as well.  Hopefully that makes sense. Let's not waste any
  41. 2:36time. Let's strap in and get started. Okay, so  how do you actually set up anti-gravity? Just
  42. 2:40head over to anti-gravity.google. They actually  have like the Google domain name, which is
  43. 2:44hilarious. and then just click on this little  download button. If you guys are on a Windows,
  44. 2:48it'll be download for Windows. Since I'm on a Mac  OS, this is download for Mac OS. Now, if you guys
  45. 2:52don't know which one of these to select. It's  pretty easy. Most modern computing applications
  46. 2:56nowadays have the ability to type like about  and then you can just go about this Mac,
  47. 3:00about this PC or whatever. And then it'll tell you  whether or not you are an Apple silicon or Intel
  48. 3:05silicon for instance with this line right here.  If I was on Intel, it would actually say like an
  49. 3:09Intel M whatever. Because I'm on an Apple silicon,  it says Apple M4 Max. And so this is the one that
  50. 3:15I need to download. If you guys are on Windows,  double check to see if it says x64 anywhere.
  51. 3:19If you guys are on Linux, you probably know more  about computers than I, so I'll stop embarrassing
  52. 3:22myself. So I'm going to give this button a quick  click. That is going to download the anti-gravity
  53. 3:26installer. On Mac, what ends up happening is we  get a little thing in the top right hand corner
  54. 3:30here, which is anti-gravity. And then all you guys  have to do is just drag this anti-gravity app into
  55. 3:34the applications folder and then let go. I already  have anti-gravity installed, so I'm not going to
  56. 3:38do that part. But that that's the installation.  It's about that easy, at least on Mac. On PC,
  57. 3:42you're going to have a little screen that pops up.  Just click accept a bunch of times until you're
  58. 3:45done. Okay. After that, what you're going to get  is a page that looks something like this. So, I'm
  59. 3:48just going to zoom in to make things a little bit  more visible. And hopefully my big head doesn't
  60. 3:51get in the way. But basically, um the way that  anti-gravity works is you have to connect to your
  61. 3:55Google account in order to get up and running.  And once you connect your Google account, you
  62. 3:58can also use um you know, Gemini as a model. Uh  the reason why this isn't popping up on the right
  63. 4:03hand side as you see is because we haven't logged  in with Google yet. So, what I'm going to do next,
  64. 4:07I'm going to click this login with Google button.  I'm then going to sign in and click sign in. and
  65. 4:10then it'll successfully authenticate you and then  take you back to the main menu. After that's done,
  66. 4:14you'll see up at the top we have a bunch more  features. In order to open up the AI feature,
  67. 4:18just click on this one on the right. It's  called your agent. There's also a little hotkey,
  68. 4:21which I use pretty often, which is just  um option uh commandB. And by doing this,
  69. 4:25I can make this pop out really quickly and  easily. Obviously, if you're on Windows,
  70. 4:28things will be a little bit different, but it's  not that bad. Now, you're inside of anti-gravity.
  71. 4:32You can actually have a conversation. So, I'm  going to say, "Hey, what's up?" I'm going to
  72. 4:35run through the UX of how to communicate with your  agent in a second, but I just wanted to show you
  73. 4:38guys how easy it is to actually get the AI part  up and running. Um, Gemini 3.1 Pro High should be
  74. 4:43provided to everybody, although with different  usage limits depending on whether or not you
  75. 4:47upgrade their plans and so on and so forth. And  you also have other models too, like 3.1 Pro Low,
  76. 4:51Gemini 3 Flash, Sonnet 4.6, Opus 4.6, and so on.  Okay, cool. So, that's just getting anti-gravity
  77. 4:57up and running. The next thing I want to do is I  actually want to explain the UX. After I explain
  78. 5:01the UX, I'll also talk about Claude Code, which  is the alternative chat window, kind of like this
  79. 5:05little agent chat widget, um, except for the Cloud  series of models that performs really, really well
  80. 5:10in specific applications, which we're also going  to use in conjunction with Gemini in this course.
  81. 5:13So, really, I want you to think about anti-gravity  as being divided into three panes. On the leftmost
  82. 5:18pane, you have basically the explorer. And for  the most part, you're only really going to be
  83. 5:22using the Explorer. You're not really going to  use the rest of these things. In the middle,
  84. 5:25you're actually going to have your file editor.  And right now, we don't have any files open,
  85. 5:28which is why we just see the anti-gravity logo.  And then on the right hand side, you actually have
  86. 5:31like your agent chat, your ability to, you know,  talk to AI. And this is how most like integrated
  87. 5:36development environments are nowadays. Um, I say  most because anti-gravity isn't really technically
  88. 5:39an IDE. There's like a couple of additional  features here, but I don't want to be pedantic.
  89. 5:43For all intents and purposes, this is an IDE. And  this is how it works. So, in order for us to see
  90. 5:47the things on the lefth hand side here, this  explore, we actually do need to open a folder,
  91. 5:50which is why it's asking us to do that. So, I'm  going to click open folder. And then I just set up
  92. 5:54this little demo for a video I recorded yesterday  called website builder. So, I'm just going to open
  93. 5:57that up. Okay. And now hopefully you guys could  see the page is transformed in this middle section
  94. 6:01is our our file explorer. So because I don't  really think files are as important these days
  95. 6:06to explore because AI does most that for you.  I usually make the lefth hand side or the right
  96. 6:10hand side way bigger. A lot of the time I actually  just issue this middle pane entirely actually and
  97. 6:15then just chat with the agent. But I'll I'll show  you guys how that works later. For now let's learn
  98. 6:18this on the left hand side here. As you see this  is just a file explorer like anything else just
  99. 6:22like a finder on your computer or whatever. You  know you have the exact same thing here. So, you
  100. 6:27know, in my case, I'm scrolling through my Mac uh  files and and folders and stuff like that. Well,
  101. 6:32that's basically exactly what anti-gravity does.  It just does it for you in a slightly different
  102. 6:35user experience. And so, folders in this case have  this little folder icon, right? Um specific types
  103. 6:41of files which have different file endings have  other logos and stuff. This is a markdown file,
  104. 6:46which is why it's an M and then it's a down. Uh  this is an HTML file, which is why it looks like
  105. 6:50that. And, you know, you don't actually need to  know a ton of programming in order to get all of
  106. 6:53this stuff. To be honest, um I don't have a formal  programming degree or anything like that. I still
  107. 6:58understood this stuff just fine after spending a  little bit of time inside of this dashboard. So,
  108. 7:01just to prove to you guys that, you know, we're  in a file. Uh if I click on this index.html here,
  109. 7:05you see that I actually have like a website file  set up here. HTML is the um ending for websites
  110. 7:11basically. And uh you know, there's a bunch  of different text here in this middle editor.
  111. 7:15Doc type, HTML head, meta, right? I don't actually  know what most of this stuff means. I just have my
  112. 7:20agent deal with it. But it is important from time  to time to at least be able to poke into the file
  113. 7:24and and do things and stuff like that. Just like  you can do with any file explorer, you can create
  114. 7:28new files here. So I can make like another file  MD. Then I could write stuff. Hey stuff. Okay.
  115. 7:34Um you can also delete files. So rightclick  and then you can you know delete, rename,
  116. 7:38open timeline. You can do all sorts of random  stuff with this. But I just want you to treat
  117. 7:43everything on the lefth hand side as basically  your average run-of-the-mill file explorer. And
  118. 7:46then the stuff in the middle you can almost treat  like like notepad on Windows or like Apple notes
  119. 7:50in the middle. Um it's just because in programming  typically specific character sequences are tied to
  120. 7:56specific pieces of functionality. You'll see here  that like it's quite colorful like link tags look
  121. 8:00a specific way. This thing looks another way. If  I go into I don't know this Tailwind config. You
  122. 8:06see we now have the color purple and and yellow.  Basically they just make it look like a freaking
  123. 8:11rainbow. And that's cool cuz why would I be  working on something gray dull and featureless
  124. 8:15if I could be working on a rainbow instead? On the  rightmost side of the file explorer, you also have
  125. 8:19the ability to like um have like a quick highle  overview of the file. So that's kind of neat.
  126. 8:23I don't know if you guys could tell super well  here, but this is basically like a I don't know,
  127. 8:27it's like a a level of abstraction up. It's like  a window that allows us to scroll up and down.
  128. 8:30This is useful if you're looking for specific  things within the file. Although I'll be honest,
  129. 8:33I mean like nowadays, as I mentioned, I don't  really use the editor too much. And then up at the
  130. 8:37very top right hand corner, this is relevant if  you run any markdown files. If you click on this
  131. 8:42little button here, and by the way, most files  nowadays where you communicate with the model
  132. 8:46are going to be markdown files. Instead of it  looking kind of like dull and drab and you know,
  133. 8:51all this tiny text here, if you click on this  little button here, you'll actually open what's
  134. 8:54called a markdown preview. And then this markdown  preview will actually like make the text the way
  135. 8:57that it's supposed to look. So every time in  markdown, you have this little like number
  136. 9:01sign. What that actually refers to is that refers  to like a heading. And that's like the really big
  137. 9:04heading. If you have two, then that's a little  smaller heading. Then you have like text down
  138. 9:08here. So, most of the time, this is what you guys  are probably more familiar with. And to be honest,
  139. 9:11a lot of the time, if I just want to like take  all this dense stuff and then make it look a lot
  140. 9:15better, I'll go back to um my browser and then  I'll go to Google Docs. And then what I'll do
  141. 9:20is I'll actually paste this in. And then I'll  just change the text color to black. And then
  142. 9:25now everything here just looks like a big Google  doc. And I can read through it. And you know,
  143. 9:28I see like orders of um hierarchy and and stuff  like that. Not super important, but good way for
  144. 9:32you to like quickly take a look at prompts.  Okay, a couple of quick hotkeys here. Um,
  145. 9:36you can go forward just uh with this. You can go  backward with this. It's the exact same hotkeys
  146. 9:40that you use on um, you know, Windows or Mac to  like change tabs and stuff cuz basically what
  147. 9:45we're doing is we're just changing tabs. So,  if you're alt tabbing, you can alt tab through
  148. 9:49files like that. Super easy. And then you'll also  notice that there's just different types of files
  149. 9:53depending on what you're looking at. So, we talked  about markdown. This is a JSX. This is a CSS. This
  150. 9:58one over here though is actually a Gemini specific  one called walkthrough where it runs you through
  151. 10:01what the AI uh basically wants to do next. It  basically teaches you what it's doing. It's kind
  152. 10:06of neat and we're going to cover a lot more about  that later. But there's cool features like review,
  153. 10:10you could submit a comment, you could ask the  model for stuff and and download it as well which
  154. 10:14is kind of cool. Okay. And then finally just to  round out our AD20 on the right hand side we have
  155. 10:18the agent panel. And this is where I'm going to  spend most of my time because as mentioned this
  156. 10:21is where like AI does most things for us nowadays.  And we don't actually have to worry too much about
  157. 10:25the folders or the files or the code. What we  worry about is we just worry about specifying what
  158. 10:29we want in natural language. That's really what  like the vibe and vibe coding is all about. Okay.
  159. 10:33So, starting at the very top right hand corner,  if you want to start a new conversation, you just
  160. 10:37click this button. Now, we don't actually have any  text in our current conversation, so I can't start
  161. 10:41a new one. If I just write a, then I can click  this. Now, I'm in a new conversation. You'll
  162. 10:45also see down here that our history is populated.  And we can see 4 seconds ago, I had the letter A.
  163. 10:50Uh 24 hours ago, I asked some questions about  background images loading and stuff like that.
  164. 10:53really quick and easy way to create a new convo.  Um, you can obviously also just use hotkeys. So,
  165. 10:58command shift L will just automatically pop one up  and then, you know, every time you type, you can
  166. 11:02just make a new one and so on and so forth. Over  here are past conversations and so this will have
  167. 11:07uh basically a list of every conversation I've  ever had with AI. So, refining prompt for website
  168. 11:11generation 47 minutes ago. This is something that  I produced. Uh, when you click on that button,
  169. 11:16it'll say, "Hey, should we open in the current  window? Should we open in a new workspace?" So,
  170. 11:19what I'm going to do is I'm going to open in a  new workspace. It'll open up a new folder. And
  171. 11:22now it'll actually pull through my conversation as  well as the specific file that I had open when I
  172. 11:26did this. In my case, I was preparing a website  uh prompt basically a website generator prompt
  173. 11:31for this course uh which is right over here and I  was just having a back and forth for that. On the
  174. 11:36right hand side, we also have additional options  which allows us to do things like customize and
  175. 11:39MCP servers. Customizations are pretty cool.  Basically what you can do is you can define
  176. 11:43highle rules that guide the behavior of your AI  model. So, we're going to get into ways to steer
  177. 11:48things as I mentioned in the um sort of outline of  this course, but rules are really quick and easy
  178. 11:52ways that you can either set globally or within  the specific folder that you're operating, okay,
  179. 11:57to either control all instances of every line of  code or every conversation you have with Gemini
  180. 12:04or you can do that within a fold. So, you can  see here I technically already have a rule and
  181. 12:08it's called cinematic landing page builder  role. Your role is to act as a world-class
  182. 12:12senior creative technologist and lead front-end  engineer. you build highfidelity cinematic one
  183. 12:16to one pixel perfect landing pages. So this is  sort of like my highle um workspace rule that
  184. 12:21helps constrain the behavior of the model.  And you know this is actually pretty long,
  185. 12:25right? Like you could scroll down this for quite  a while. Um this is one of the reasons why I have
  186. 12:28pretty good vibecoded quality because I basically  put in a lot of style guide and highle information
  187. 12:33to help the model you know make quick decisions on  the fly without having to ask me for stuff. So you
  188. 12:37can define that both globally or a workspace. If  you just click the button then you can enter the
  189. 12:41information right over here. You click this button  and you can just um create your new rule. So maybe
  190. 12:45I want it to be called design guide. Oh, and you  have to use um you know hyphens in between each.
  191. 12:50You can't actually have any spaces. I'm just using  a little voice transcription tool. In this case,
  192. 12:54this one's called whisper flow. Um and then you  know you can basically specify an activation mode.
  193. 12:59Is it always on? Is it manual? Do I set it? Do uh  I leave it up to the model or do I do glob which
  194. 13:06applies specifically to files that match some file  pattern? In practice, I never use glob. I never
  195. 13:11use model decision. I never use manual. I always  use always on. So in this case, I'd say, hey,
  196. 13:15when you design websites, I want you to stick to a  minimalistic, sleek aesthetic. I want you to build
  197. 13:19things that are significantly closer in design to,  let's say, the Apple homepage than anything else.
  198. 13:24And I can populate that. If I wanted to run this,  I would just save this file. And as you can see,
  199. 13:27we've now added that as a rule. Now, I  don't actually want this rule here. Um,
  200. 13:31so what I'm going to do next is I'm just going  to delete this. The way you do so is every time
  201. 13:35you generate a rule, it's now created inside of  agent/ruules folder. So if you want to delete it,
  202. 13:40you just delete that. And now we're back to just  that one rule which is called the gemini.mmd. This
  203. 13:44gemini.mmd is basically just the parent rule that  always applies if you have a file called capital
  204. 13:49gemini.mmd in your workspace. All Gemini models  will just always take that as a rule. Um multiple
  205. 13:54different ways to define rules and stuff like  that as well. Not super important. There's also
  206. 13:58workflows which I think are probably nowadays  better understood as skills where basically
  207. 14:02similarly to rules you can define behaviors or  specific sequences of steps that you want your
  208. 14:06agent to take every single time. So these can  be pretty cool and you can again define them
  209. 14:10as global or workspace. So I could call this I  don't know code review here. I could say this
  210. 14:15workflow defines a code review process that goes  through the code and then maximizes the security
  211. 14:20of the vibe coded app. To start with, I want you  to reference this document. This document includes
  212. 14:24information about all sorts of high ROI security  practices for vibe coded apps. After you're done,
  213. 14:29I'd like you to go through each of these step  by step. Uh make small incremental changes to
  214. 14:33the codebase. Try not to, you know, do everything  everywhere all at once. and then verify with me
  215. 14:38at the end that it works by asking me to test  it before we push to production or anything
  216. 14:42like that. And so, you know, in this case, what  I've done is I've I've built some quick little
  217. 14:48rule here. And then maybe over here is where I  put like my security stuff. And now, you know,
  218. 14:53what I have is I have a quick little workflow  that after I'm done building my vibe coded app,
  219. 14:57I can just say, "Hey, I want you to run the code-  review workflow." and then it'll just go through
  220. 15:01this standard operating procedure, the sequence  of steps, more similar to like the way that a
  221. 15:06business would operate with checklist style  tasks. Again, I don't actually want this. Um,
  222. 15:10so what I'm going to do is I'm going to go  back here. I'm just going to delete this.
  223. 15:12That'll delete the code review customization.  Now, there's also some other customizations
  224. 15:16like MCP servers. I'm going to talk a little bit  more about MCP servers later. But the way I want
  225. 15:20you to treat MCP servers for now is basically  it's just a way to define workflows. It's just
  226. 15:25um workflows that somebody else did for you.  And so these MCP servers essentially allow
  227. 15:29you to connect to different tools and then run  standardized workflows on those tools. So for
  228. 15:33instance, if I wanted to use a server like a  PostgresSQL, there's a pre-existing workflow
  229. 15:38bundle here called CloudSQL for PostgrSQL. This  is a specific database language and specific
  230. 15:44type of database. This basically just defines  a checklist series of steps that the model will
  231. 15:48always do to communicate with us that I don't  know can translate my natural language queries
  232. 15:52into that if I wanted to. Same thing with Looker.  Same thing with GitHub, Neon, Stripe. Basically,
  233. 15:58these just allow us to communicate with different  tools in a very predictable way, which as I'm sure
  234. 16:02you can imagine if you're building high quality  vibe coded apps can be pretty useful. That said,
  235. 16:06there are also some downsides to MCP server.  So, I don't really use them a lot in practice,
  236. 16:09and we'll cover all that stuff later. For now,  I don't want to overwhelm you. Okay, next up, we
  237. 16:14have the title of the current folder. As you can  see, this one's just called website-builder, not
  238. 16:17rocket science. Then, we have the ability to add  some context here to our prompt. So, if I wanted
  239. 16:21to, I could add media. I could add mentions. And  I could also add workflows. Remember the little
  240. 16:25workflow that I put together earlier and then  deleted? If I had workflows, every time I wrote
  241. 16:29slash, I would automatically be able to add them  here. What's cool though is you can also mention,
  242. 16:32and when you type mention or or you just press at,  then you can actually attach files, directories,
  243. 16:37uh, code context items, rules, even terminals,  pre-existing conversations, and then also MCP
  244. 16:42servers into the context. And the reason why this  is valuable is because, you know, I could just
  245. 16:47copy everything in this file and paste it in, or I  could just say, "Hey, I want you to reference this
  246. 16:51gemini.md." And then it would do the same thing,  but as you can see, I'm not really polluting this
  247. 16:54big window. It's very clear and clean. After that,  you have the mode. Now, there are two conversation
  248. 16:59modes available to Gemini 3.1 Pro right now.  There's planning and fast. This may change at
  249. 17:03a certain point in time, but for now, this is more  than enough. In general, you always want to start
  250. 17:07in planning anytime you're designing or building a  new feature. Planning is good because it basically
  251. 17:11allows the model well almost forces the model  to do a lot of thinking before it actually like
  252. 17:15you know stretches its fingers out in the world  and starts manipulating files and stuff. It then
  253. 17:19actually presents you a workflow and says hey this  is what I'm planning on doing. Are you sure you
  254. 17:24want me to do this? And then you can set your own  behavior to either auto approve which is just have
  255. 17:28it run on its own um decided plan or you could  actually stop it and say hey I didn't really like
  256. 17:33what you did here. I want to make a minor change.  Next up you also have fast. fast just allows it
  257. 17:38to execute things directly and go really quickly.  And so this is actually pretty useful if you're
  258. 17:42doing quick one-off tasks. Hey, I want you to  change this file format to this file format. Hey,
  259. 17:46I want you to change this markdown file to a txt  file. Hey, I want you to, I don't know, refactor
  260. 17:50XYZ really quickly with this um, you know, brief  little variable in mind or something like that.
  261. 17:55Okay, so in general, I always start with planning  and then at the end um, you know, when I'm just
  262. 17:58doing one-off tasks and stuff, if I need to, I'll  use fast. Underneath, we have the model picker,
  263. 18:03which I've already covered. includes the specific  one you want to pick and choose and actually have
  264. 18:07in communication with. Remember how earlier I  said the agent is just like a wrapper for the
  265. 18:12um specific model you're talking to. Well, this  is how that works, right? This chat window isn't
  266. 18:16communicating with all models right now. It's just  communicating with one, but I can hot swap them
  267. 18:20anytime. Instead of Gemini 3.1 Pro high, I could  easily choose Gemini 3.1 Pro Low. And you'll find
  268. 18:24that every model has different pros and cons.  If you want a quick example of pros and cons,
  269. 18:29just go to Google and type Gemini 3.1 Pro High  versus Low. And what you'll do is you'll have um
  270. 18:34you know basically benchmarks showing you how high  quality the models are at different things. Uh
  271. 18:39use usually some sort of like graph here that runs  through hey you know highs 44.4% on this benchmark
  272. 18:45lows 39.8% on this other benchmark and so on and  so forth. I will say in general I tend to just use
  273. 18:50like the best models currently available and to be  honest that's usually the most recent model that
  274. 18:54has been pushed out by the big three companies  right now which tend to be Google um OpenAI and
  275. 18:59then Anthropic. Uh I was all about you know claude  uh Opus 4.6. six just last week. Um, now you know,
  276. 19:04Gemini 3.1 Pro High seems to be very, very good  at like design specific applications. So, what
  277. 19:09I'm doing is I'm passing off my design stuff to  Gemini 3.1 Pro High. Then I have Opus 4.6. Kind of
  278. 19:14clean stuff up on the back end. Yeah, this is how  you select through a bunch of different models.
  279. 19:17And as you can see, it's just like Lego blocks.  They're hot swappable. Gemini 3 Flash is super
  280. 19:21super quick. Sauna 4.6 is a really long context  window. A lot of these have pros and cons. Um,
  281. 19:26nobody really uses this in practice though. Okay.  And then finally, um you can click this button to
  282. 19:30replace your texting with basically talking.  So what I'm doing right now is I'm just having
  283. 19:34a normal conversation with it. When I press  this button, um you know, and then I I send it,
  284. 19:40Gemini has a built-in uh mechanism to just  transcribe what I just said and then turn that
  285. 19:44into text. The reason why this is valuable and why  you're seeing a lot of people use voice dictation
  286. 19:48tools nowadays, it's because on average, people  speak much faster than they write. If I'm writing
  287. 19:51at 50 to 80 words per minute, I can speak at like  150 to 200 words per minute. So, it's obviously
  288. 19:56a lot faster and a lot quicker. Now that I've  actually sent a message, you could see how the
  289. 20:00UX has changed a little bit. We now have a thought  little tab. This basically runs you through the
  290. 20:04internal thoughts of the model. The reason why  they make this present and visible to you is
  291. 20:08because if it's making any sort of like egregious  error, you can just quickly dive in and say,
  292. 20:12"Okay, so why did it make that error?" This gives  you some transparency, some accountability, and
  293. 20:16then you can, I don't know, adjust your feature  prompting style to be better to solve that issue.
  294. 20:20It's also good because sometimes the models are  lazy and they don't really respond because they're
  295. 20:24trying to conserve tokens or whatever the heck.  This is a quick and easy way to like make sure
  296. 20:27that the internal thing is not uh the user asked  me this question. I don't really want to spend a
  297. 20:31lot of tokens. So I've decided to give them a much  simpler answer. This is how you can actually just
  298. 20:35figure out what's going on under the hood. The  text that is not sort of this darker thinking
  299. 20:39tab is uh the response. And so in this case to  get started on building a cinematic landing page,
  300. 20:43please please answer the following questions. The  reason why it's running me through that is because
  301. 20:46I've defined that as basically my highle workflow  rule uh or sorry just rule in gemini.mmd. I'm
  302. 20:53saying hey you know I want you to act as a world  class senior creative technologist when the user
  303. 20:57asks something immediately asked exactly these  questions and then it's asking me these questions.
  304. 21:02So basically this is taking everything from that  initial configuration file and then despite the
  305. 21:06fact that my voice message said nothing of any  import uh it just injected that up at the very top
  306. 21:11and now it's trying to you know do my my higher  level rule instructions. Okay so underneath you
  307. 21:15have good or bad. Uh this is just a way that  you can help train the Gemini models on like
  308. 21:19hey I like this response. Hey I don't like this  response. I never really use that in practice.
  309. 21:23And now you can see that there's also a bunch of  additional tabs that I've opened up here. On the
  310. 21:26lefth hand side there's changes overview. if your  request changed any files um you know on your work
  311. 21:32inside of your folder that's actually going to pop  up right here and then you can just take a look at
  312. 21:35them in practice nowadays basically nobody takes  a look at these they're just like oh yeah man you
  313. 21:39figure it out you got it uh next up is terminal  so sometimes Gemini or other models will launch
  314. 21:44terminal instances for you can actually see the  background processes running in that tab artifacts
  315. 21:48or files that are part of the conversation so you  know I added this gemini.md file for instance I
  316. 21:53mentioned it right and then over here we have  the browser and this is kind of neat you can
  317. 21:57actually launch a browser are inside of uh Gemini  nowadays. Um this browser, you know, I'm not going
  318. 22:01to say it's like the highest quality browser on  planet Earth, but it can be pretty cool. If I go
  319. 22:05over here, you could see um we're going to keep  it. We're now opened on the anti-gravity uh docs
  320. 22:12page for browser. And so, you know how some things  in life you can only really do on a browser? You
  321. 22:16can't just do everything via API or you can't  do everything like through a chat window. This
  322. 22:20is basically a quick and easy way that allows you  to do that. And I'm not going to say that this is
  323. 22:23like super super valuable or really really  all that helpful right now, but you know,
  324. 22:27it's pretty cool and obviously they're trying  to push more towards browser automation. Okay,
  325. 22:31so hopefully you guys now know everything about  how to use anti-gravity and then the Gemini series
  326. 22:35of models. What I want to do next is I just want  to give you guys a quick run through of Claude
  327. 22:38Code because we're also going to be using that.  Basically, the Claude large language model lives
  328. 22:42within the Claude code chat software which we also  wrap inside of anti-gravity. And so just the exact
  329. 22:47same thing that we just did with the agent chat,  we can do with the Claude code chat as well. So
  330. 22:52what I'm going to do next is I'm actually going  to exit out of this view. Okay? And then I'm going
  331. 22:55to sign up to Claude. Now, in order to use Claude  Code, you do need an account. So what you have to
  332. 22:58do is you have to go over to claude.ai. That'll  take you to a page that looks like this. And
  333. 23:02then you can enter some information here and then  continue with your email. I don't actually have an
  334. 23:07email called asf asdf asdfgmail.com. If I would,  I'd probably be a billionaire. Um, basically
  335. 23:12what'll happen is they'll send you a link over to  your email. You can click on that link and then
  336. 23:16it'll sign you in. From there, you have a brief  little onboarding that you need to fill out and
  337. 23:19then that'll take you to the most important part,  which is the pricing. Now, the way that the plans
  338. 23:24work for Claude Code is you need to select between  the pro or the max plan. Pro plan is $17 a month
  339. 23:31right now. The max plan starts at 100 and it can  be significantly higher. Unfortunately, right now
  340. 23:36they don't allow you to use quad code within a  free plan. That's just part of the limitations
  341. 23:40of using the cloud family of models and it's just  always a trade-off with these things, right? Like
  342. 23:44if you think about it, Gemini allows you to use  things for free. Uh Google, sorry, allows you
  343. 23:48to use Gemini for free despite not having to pay  any money, but then you have quite limited usage.
  344. 23:52Whereas Cloud Code requires you to sort of put  a certain minimum amount of money, in this case
  345. 23:5617 bucks a month in order to use it, but then it  tends to be a lot better at specific applications.
  346. 24:00So you don't have to necessarily sign up for  this, but if you did want to sign up for it,
  347. 24:04if you wanted to use um you know, Vibe Coding in  a way that I'm going to show you in this course,
  348. 24:08you would have to have some sort of subscription  ongoing. I don't want to push you guys to sign up
  349. 24:12to anything. I'm not affiliated with, you know,  Anthropic. I'm not affiliated with Claude Code.
  350. 24:16I'm not pushing any specific product on you in  this course. I will just say that I, as a business
  351. 24:20owner, uh, you know, I get a tremendous return on  investment from this stuff. Just a few months ago,
  352. 24:25in order to hire a developer at the level of Cloud  Code or, you know, Gemini with an anti-gravity,
  353. 24:30I would have had to spend 20,000 to $30,000 a  month. I would have had to go down to Silicon
  354. 24:34Valley and find like a super cracked dev and then  hire them on my team. And those people would work
  355. 24:39eight hours a day max. Um, this stuff does 24  hours a day. This stuff you can plug in APIs. It's
  356. 24:44totally automatable. This stuff gets smarter every  day, week or month. And so this is really like the
  357. 24:48technology of the future. Um, I probably get at  least 100x ROI on the money that I spend and I'm
  358. 24:52spending like $200 a month, right? So that's  that for Claude. Once you're done signing up,
  359. 24:57um, what'll happen is we can go back to  anti-gravity, go to this bottom lefth hand
  360. 25:01tab here called extensions, and then click cloud  code for VS Code. Now what this is is just like
  361. 25:06the agent chat on the right hand side is the way  to communicate with the Gemini series of models.
  362. 25:10This is built by Google. Okay, this is built by  Enthropic and it's just a little extension chat
  363. 25:14that you can put into in gravity. And so what I've  done here is I've already installed it, but you'll
  364. 25:18have to install it. When you get it installed,  what you can do is you can click on this little
  365. 25:21button in the top right hand corner. That'll open  up a clawed code window just like this. Okay. And
  366. 25:26as you see, very similar UX to what we had earlier  with the agent chat. Just this time now it's
  367. 25:30sort of like cute and orange and there's a little  space invader over here. So really quickly to run
  368. 25:34you through it, if this is the very first time  you've done this, you do need to go /lo. Okay,
  369. 25:39that'll allow you to log in to your Claude AAS  subscription which you just put together a moment
  370. 25:42ago. You can also sign in through the anthropic  console or these other thirdparty providers. Most
  371. 25:46people for cost purposes are going to choose this  as the cheapest one. After that, you just write
  372. 25:50a message like, "Hey, what's up?" Now, just like  you were communicating a moment ago with Gemini,
  373. 25:54now what we're doing is we're communicating  with a different model. And you can find out
  374. 25:58which model by clicking the bottom right hand  corner and then going to switch model. And so,
  375. 26:01right now, I'm using this default recommended  one, Opus 4.6, most capable for complex work.
  376. 26:06There's also another one, Opus 1 million context.  There's Sonnet, Sonnet 1 million context, Haiku,
  377. 26:11and then uh some custom 4.6 model down here.  I think if you guys are keen viewers, you'll
  378. 26:16probably say, "Well, wait, Nick, didn't we have  the ability to communicate with the Claude series
  379. 26:20of models down here?" And the answer to that is  yes. Uh for whatever reason, I guess just because
  380. 26:24of the nature of their business arrangement, um  inside of the agent chat and anti-gravity, Google
  381. 26:29actually allows you to communicate with the Claude  series of models as well. But in my experience,
  382. 26:32and I don't know if this is because they're  trying to handicap it or something like that,
  383. 26:35but like in my experience, it just doesn't work  as well inside of that agent chat. And the UX is
  384. 26:39actually much better within the Claude chat.  So, what I typically do is I just communicate
  385. 26:42with the Cloud series of models in Claude Code  and then I communicate with the Gemini series
  386. 26:46of models in their built-in anti-gravity agent  chat. And that works really well for me. Um, also
  387. 26:51it doesn't it like simplifies my payments. So, I'm  like paying one provider for one sort of model and
  388. 26:55then another provider for another sort of model.  Obviously, your mileage may vary with that. And
  389. 26:58maybe it's just the vibes and vibe coding that are  getting to me. I much prefer to communicate with
  390. 27:01Claude in the Claude code extension. Anyway,  hopefully it's pretty clear. Same thing. You
  391. 27:06have little text windows, right? This is its  reply down over here. Just like in um Gemini,
  392. 27:10we had a few modes like planning and so on and so  forth. In this one, we have um ask for edits, edit
  393. 27:15automatically, plan mode, and then also bypass  permissions. Uh most Gemini is automatically
  394. 27:20set to bypass permissions now. So, you don't  actually have to like manually set it. Ask
  395. 27:23before edit is just where if you want to change  the pre-existing files on the lefth hand side,
  396. 27:27you need to just like verify with me first. So, if  I say change readme.md to include a snippet about
  397. 27:35Nick Sarif, okay? And then I ask it to do this,  what it'll have to do is it'll have to go find
  398. 27:40some information about Nick Sarif. Then it'll have  to read it. Then it'll have to make some proposed
  399. 27:43adjustments. But do you see how now we have this  little panel that's popping up saying, "Hey, do
  400. 27:47you want to make this edit?" So I could say yes.  I could allow all edits this session. And I could
  401. 27:51say no. Or I could tell Claude what to do instead.  I'm just going to escape out of it. That's how Ask
  402. 27:54Before edits works. Most people are going to use  edit automatically because then you can change
  403. 27:58pre-existing files without actually having to like  do that little, you know, hey, should I change
  404. 28:02this? Uh because nowadays these models just move  so much faster than human beings ever can. There's
  405. 28:06just no need to. And then finally, you have plan  mode, which is similar. It just does a lot of
  406. 28:10thinking. Doesn't actually do anything until  it presents the plan to you. And then finally,
  407. 28:13a bypass permissions, which is uh you know my  yolo mode where I just say do it again and then
  408. 28:18it's not going to ask me for anything. It's just  actually going to go edit the file. Right. So
  409. 28:21now it says built by Nick Sarif. I'm a software  engineer and automation consultant specializing
  410. 28:25in AI powered tools and web applications. Thanks  so much. The software engineering title has never
  411. 28:30been easier to get. Okay, everything else you  are going to learn by doing. Hopefully, this
  412. 28:33has been a comprehensive setup and you guys now  know how anti-gravity works in conjunction with
  413. 28:37the agent chat and then the Gemini 3.1 Pro series  of models. You also know how anti-gravity works in
  414. 28:42conjunction with Claude Code and then the Claude  series of models. And you also understand the
  415. 28:47interface, at least the 8020 of the interface that  we could use to build our very first project. Next
  416. 28:51up, what we're going to do is we're going to build  a highquality, simple portfolio site in just a few
  417. 28:56minutes that I'm then going to push live onto the  internet. I'm doing this because I want to show
  418. 29:00you guys how simple and easy it is to actually  develop like actual web applications and web
  419. 29:04properties with Gemini 3.1 Pro High. And I'm also  going to include all the prompts and everything
  420. 29:08you need to do the same thing on your end down  below in the description. So, just check that free
  421. 29:12folder out. Okay, so the simplest and easiest way  that I have found to set up websites with Gemini
  422. 29:173.1 Pro high is you literally just provide it a  simple copy paste prompt which I have down below
  423. 29:24in the description and you guys can use as your  end all be all or you guys could use as a base to
  424. 29:28make your own prompt on top of. Okay, store that  as a gemini.md and then just fire it off. So, what
  425. 29:34I've done here is I basically open up a new folder  called website builder-demo with the gemini.mmd
  426. 29:39with this big long prompt. And I'll run through  the prompt in a second while I'm actually creating
  427. 29:42the website. But then I say build me a website.  Now, what this does is this forces the model to
  428. 29:50act as a world-class senior creative technologist  and lead front-end engineer. Basically, we're
  429. 29:55saying you build highfidelity cinematic 1:1 pixel  perfect landing pages. Every site you produce
  430. 30:00should feel like a digital instrument. You must  eradicate generic AI patterns, including typical
  431. 30:05structural layouts like a standard hero, three  column features, and CTA. Every site you build
  432. 30:09will use a vastly different structural layout,  typographic scaling, and interactive paradigm
  433. 30:13based on the chosen archetype and structural  typology. Kind of a mouthful, right? Now,
  434. 30:18I'm not going to run through all the rest of  these, but basically, to make a long story short,
  435. 30:21this section here is just guiding it through a  brief little Q&A so that you can choose, you know,
  436. 30:26the highest quality website design for you. This  over here has a bunch of different aesthetic
  437. 30:30archetypes depending on what you're looking at  which we can select. Down below we have some
  438. 30:35structural typologies including bento grids,  split screens, infinite horizontal structures,
  439. 30:40linear narratives, and then application shell  which is kind of neat. Then we have some brief
  440. 30:45little rules about different tools to use just  based off of my own understanding of tooling. Um
  441. 30:50as well as um some double-checking protocol down  here. And on the right hand side, as you can see,
  442. 30:55after I entered that little uh message, it's now  asking me for the brand name, the core thesis, um
  443. 31:00aesthetic archetype, structural typologies, three  core pillars, and then the ultimate conversion
  444. 31:04goal. So, all I'm going to do now is I'm going  to close out of this. Okay. Make this way way
  445. 31:09bigger just so I could see like most of it. And  then I'm just going to enter my information. So,
  446. 31:15uh my brand name, just so people are all on  the same page as me, is called Leftclick. And
  447. 31:19basically what we are to zoom way in there because  the website looks like trash right now is we're
  448. 31:23the definitive AI growth partner for fastmoving  B2B companies. This is a website that I actually
  449. 31:28had a real developer like I paid somebody money  to put this together for me cuz I didn't have
  450. 31:32the time. And the whole idea is we're like an  AI automation boutique shop that helps people
  451. 31:36generate revenue using high growth systems. This  is typically stuff like cold email systems. It's
  452. 31:41stuff like speed to lead systems for paid ads  and so on and so forth. So it's pretty neat,
  453. 31:45right? It's pretty sexy. We got the cool photo  with Hormosi and Ovens over here. That's uh won me
  454. 31:49some goodwill for sure. Basically, what I want to  do is I just want to have AI try and generate uh
  455. 31:53this website instead of me. And then I just want  to compare and contrast the results. You'll see
  456. 31:57there's some mild things here like there's a cool  little animation that kind of follows my mouse
  457. 32:00around. That's kind of neat, right? Obviously  the text and the fonts and stuff that those are
  458. 32:03very sexy. So, do you think AI could do as good  of a job? Well, let's find out. I'm going to
  459. 32:07answer some information here. Brand name is called  Leftclick. We help high growth B2B companies scale
  460. 32:14revenue using outbound methods like cold email.  Two, pick best fit. Three, pick best fit. Four,
  461. 32:23super low cost of acquiring a customer. Um, AI  based personalization, which lets us attack at
  462. 32:31both scale and high levels of perceived  personalization. And then trusted vendor.
  463. 32:41We've worked with multi-billion dollar portfolio  companies. And then ultimate conversion goal is
  464. 32:48book a growth mapping call 30 men consult. Just  going to enter this information now. And I'm going
  465. 32:56to have the model do everything else for me. The  first thing that's going to pop up is this little
  466. 33:00thinking tab. And so what it's doing if I scroll  to the very top is it's focusing on refining the
  467. 33:04initial approach particularly concerning file  operations. It's prioritizing the use of more
  468. 33:08specific resources to manage and manipulate  information and so on and so forth. These are
  469. 33:12all of its own thoughts. And basically the way  that this works is at every step it's basically
  470. 33:17like another it's like another run. It basically  takes the prompt, it sends it, it does a bunch of
  471. 33:21thinking and then it sends that back to another  instance and says what's next over and over and
  472. 33:25over and over again. So that's what's happening  down over here at the bottom. Once you're done
  473. 33:29something that requires a fair amount of planning,  it'll actually pop open a planning uh section. And
  474. 33:33this basically runs through the files that were  edited as we saw earlier. Okay. the progress
  475. 33:38updates of that, some additional thinking, and  then finally a task list for what it's planning
  476. 33:43on doing. When tasks lists pop up, they pop up in  the middle over here. And as you can see, we have
  477. 33:48a leftclick dashboard landing page. It's going  to start by scaffolding the application using
  478. 33:51a particular library. Then it's going to install  dependencies, configure Tailwind, then it's going
  479. 33:56to build a core layout, and then, you know, go  through and do things in a really high quality
  480. 34:00way. Okay. So over here, what it's doing now is  it's running a terminal shell. Terminals just look
  481. 34:05like this. uh running background command. Anytime  you see anything like this with this little
  482. 34:09terminal icon, it's basically just doing the thing  in the terminal for you. Um you can actually just
  483. 34:13jump to that anytime you want to. And here you can  actually see like what it's communicating with,
  484. 34:18what it's doing. You can also see the artifacts.  So there's now two artifacts that it's created.
  485. 34:22One's called uh the task and the other's called  the implementation plan. Both of these here are
  486. 34:26basically just resources for you to make things a  little bit more visible. Like logically speaking,
  487. 34:31this model is doing a lot under the hood, right?  writing hundreds, thousands of of words basically
  488. 34:35every few seconds. Um I have no insight into this.  This is all just occurring behind the scenes.
  489. 34:39And so one of the big issues right now with vibe  coded apps is there's just no interpretability or
  490. 34:43accountability about like what the model's doing  underneath um you know behind everything. Well,
  491. 34:47this implementation plan, the whole idea is it  just like shows you behind the scenes what's going
  492. 34:51on. Well, it's decided on some AR aesthetic and  typology decisions like um B2B SAS dense. We want
  493. 34:57gunmetal safety orange steel. The typography is  going to be IBM Plex suns, IBM Plex mono, right?
  494. 35:03These different fonts and so on and so forth. The  application shell is going to look like this. The
  495. 35:07proposed changes are going to look like that. As  you saw a moment ago, we just added a file to our
  496. 35:11folder called leftclick- dashboard. If I give this  button a click, you'll see we now have a bunch
  497. 35:15of files that it's written. The model just wrote  all of this while I was just talking to you guys,
  498. 35:19and it's currently writing more, right? Which is  pretty neat. I don't know how any of this stuff
  499. 35:23works, to be honest. And I don't need to anymore.  I just vibe code. If I like it, fantastic. If not,
  500. 35:28I I'll ask for changes and I'll show you guys  what that loop looks like in a second. But yeah,
  501. 35:32I mean, you know, as you guys see, a big chunk  of this is just shephering AI and making sure
  502. 35:36that it's operating in in the right direction, the  direction that you want, as well as looking over
  503. 35:40things like implementation plans, intermediary  files that are created, and stuff like that to
  504. 35:44just ensure that like everything is going the way  that you initially planned. What I'm going to do
  505. 35:47next is I'm going to go grab a sip of water and  then I'll come back and hopefully this website
  506. 35:50will be ready to go. Okay. And here is the result.  Deploy the growth engine. We build growth systems
  507. 35:55for high- rev B2B agencies. Pure information  density, zero latency scaling. Wow, that's
  508. 35:59cool. Ooh, I love that button. That's really nice.  Uh, if you guys watched one of my recent videos on
  509. 36:04website design, this is the same approach. So,  I actually really like the background image as
  510. 36:08well. And so, I uh turned I basically gave it the  ability like the prompt that you guys are going to
  511. 36:12use if you copy the prompt and use it in your own.  Basically gave it the ability to like find stock
  512. 36:17image websites and stuff like that. And that's how  we end up with like this really nice clean like
  513. 36:21glass ISO form thing up at the top. then have some  cool uh you know sections here. Rapid revenue,
  514. 36:28lowest cost, proven vendor. That's really cool. We  focus on systemic growth. I like that. I like the
  515. 36:32blue this time. We got some cool animations and  stuff like that. You will find, you know, because
  516. 36:37we're using the same icon libraries and stuff,  some of these animations will be pretty similar.
  517. 36:40If you redo this five or six times, but yeah, I  mean like we just we just one-shoted a really cool
  518. 36:45website, right? Um I'm just going to do the same  thing now a couple times just to show you guys
  519. 36:48that you don't have to stick just to the style.  You could do it in a bunch of different ones,
  520. 36:51too, if you wanted to. Okay. So, I'm just going  to open up a new folder here. And then I'm just
  521. 36:54going to make one website builder new. And then  I'm just going to operate inside of this folder.
  522. 37:00Okay. This is another rendition. So, I think this  is supposed to be like kind of earthy and healthy,
  523. 37:05which is why it says leftclick with the globe.  That is definitely not our brand, but what are
  524. 37:09you going to do? We're the architect of outbound  scale. We weaponize personalization by designing
  525. 37:14and deploying outbound architect for multi-billion  dollar portfolios. Kind of really like that
  526. 37:18section too much. Here's probably the weakest bit,  though. This stuff looks really cool. Like like I
  527. 37:22I really like this. Look at that. This looks nice  as well. You know, it's like something it came up
  528. 37:27with to showcase how we're verifying decision  maker profiles. We're trusted by the best. You
  529. 37:31know, we're architecting the revenue engine. So,  this is a great example for me to show you how
  530. 37:34you can change websites to make things better  or uh I don't know, you know, include sections
  531. 37:38that you want. So, what I have here is I have a  voice transcription tool. And you know what? I
  532. 37:42I I don't really like I don't know, I just don't  really like the layout here. I think personally
  533. 37:46the navbar is kind of an issue. So, what I'm  going to do is I'm going to go and I'm going
  534. 37:50to see if I could find a navbar from something  else and I'm just going to include a screenshot.
  535. 37:57So, like this navbar is actually really  cool, right? Like this this is clean. So,
  536. 38:00why don't I just take this navbar from my former  site? Okay. And then why don't I also just create
  537. 38:06a big voice prompt about all the things I want to  change. Hey, I have a navbar that I've supplied
  538. 38:11you with. I want you to make it that sort of  pill style because I think it's really high-end
  539. 38:15and clean. I don't need the Earth logo next to  left click. You can just use uh left click. Um,
  540. 38:20we should have buttons on the hero header. Also,  just make the hero header way bigger. I want it to
  541. 38:24be like huge. I want the content in there to  just pop and and explode. There's some weird
  542. 38:29numbers next to the hypereefficient acquisition  graph. Um, they're outside of the bounds of that
  543. 38:34little box. So, let's fix that up. Um, let's add  another section between scale without compromise
  544. 38:40and trusted by the best. That just talks about  me. My name is Nick Sarif. I run Leftclick. I've
  545. 38:46helped uh I don't know over 400 500,000 people  now use AI automation and then outbound methods
  546. 38:53to improve their lives and their businesses.  Um you can do a quick little Google about me as
  547. 38:57well if you want. And then down at the bottom, um  let's just add a footer in addition to the CTA so
  548. 39:03that it's just a little bit thicker and there's  more going on. Okay. And then I'm just going to
  549. 39:06dump that right here. And I'm just going to dump  that right here. So boom. Let's just remove that.
  550. 39:12Uh and then Yeah. And then I'm going to paste.  I guess I got to paste the image, right? Yeah.
  551. 39:15There you go. Cool. So, now that I've I pumped  all this stuff inside, um I'm just going to wait
  552. 39:19for it to finish the change and then I'm going to  double back. Meanwhile, I designed another website
  553. 39:23simultaneously uh for my content writing business.  Once I can copy. So, I like this. This is really
  554. 39:28clean. We then have that little pillow up top  with similar three card design here with some
  555. 39:32text. That's neat. Uh we also have these cards  that kind of come up. I really love these cards.
  556. 39:36These are really clean. And then down over here at  the bottom, we have some pricing. So, that's nice.
  557. 39:42Anyway, I just wanted to show you guys that while  we're waiting for the other leftclick site. Okay,
  558. 39:45and I can see it's saying the dev environment  is still running. So, I'm just going to copy
  559. 39:49this. Go back here and paste this in. And this  is way bigger. Look at that. This is huge. Nice.
  560. 39:56This is significantly better. I'd say that's  about the size that I wanted. And then up here,
  561. 40:01I think it's basically just one for one copied the  font. So, I'll just make one more change, which
  562. 40:05is to make sure that the style of this aligns with  the style of the site. Hey, just want to make sure
  563. 40:08the style of the pill navbar aligns with the rest  of the style of the site. Super clean. Nice job on
  564. 40:15everything else. Oh, and I'll supply you an image  that you could use. Um, for me, that will help.
  565. 40:21Really like the footer as well. It's pretty clean.  Let's make the green just a little bit darker,
  566. 40:26actually. Um, that's probably the last thing that  I want to change. Everything else here looks nice,
  567. 40:30though. Man, there's a lot of images of me out  there. We'll go large. What makes sense? Which
  568. 40:34one makes me not look like a seven-year-old?  probably this one. Let's just do that. So, I'll
  569. 40:38go here. I'm going to copy both the image and the  agent, I think. So, we'll just dump that in. So,
  570. 40:45I'm just going to copy this here, and then I'll  paste this in. Okay. And then, yeah, I should be
  571. 40:51good. And this is the finished product. Uh, what I  like is when I load it, there's that little bubble
  572. 40:56that goes out. You know, it expands at scale. Uh,  navbar is looking nice and clean. When we mouse
  573. 41:00over it, it's green. We have everything that I  asked for, including a picture of myself with
  574. 41:04like slightly darker green. And yeah, I mean,  like, you know, is this again going to win any
  575. 41:08awards? Probably not, especially since website  design is so commoditized these days. But now
  576. 41:12that I've showed you how to build sites, not just  one site, multiple sites, by the way, and probably
  577. 41:16a hundth of the time it would have taken you to  do uh websites the old school way. And I know
  578. 41:20that cuz I used to be a website designer. I used  to get paid for stuff like this. Melts my heart.
  579. 41:24Let me show you how to deploy it and how easy it  is to actually get a website like this up live on
  580. 41:27the internet uh with Vibe Coding. So, basically  what you're going to need is you're going to need
  581. 41:31a hosting provider. Now, I use Netifi because it's  simple. It's uh free for a couple of sites anyway,
  582. 41:36but you can also use Verscell and there are a  few other ones that are like this. Basically,
  583. 41:40what happens is they just take these sites that  we just put together. Okay, so whatever this,
  584. 41:44you know, link is here that I'm opening up  and then it takes the static files on your
  585. 41:50computer that you're currently accessing at  localhost 5173 and then it just like puts
  586. 41:54them on a web accessible URL. So, we're going to  have something like gentlebeaver uh.netlifi.com
  587. 42:01and we don't need to spend any money in order to  get that done. It's completely free for us. Um,
  588. 42:05it'll only cost us money if we require like a  custom URL like leftclick.ai for instance. So, I'm
  589. 42:10going to go over to netifi.com. Uh, and then I'm  going to, you know, if it's your first time there,
  590. 42:15sign up. I'm just going to click login. And I  have a bunch of different projects down over here,
  591. 42:18um, that I've hosted on Netlefi before, right?  So, make money with make reply robot leftclick
  592. 42:23go one second copies. You can see I've had quite  a few startups that have failed. Uh, and what I'm
  593. 42:29going to do now is I'm just going to click add new  project. And then uh you know I'm going to click
  594. 42:34deploy manually and then I can just drag my drop  drag and drop my project folder here. So simply
  595. 42:41put I'm going to go back to my um anti-gravity  and then what I want is I just want to rightclick
  596. 42:45this and say reveal and finder. I'm just going to  drag this whole file in. Okay, this whole thing.
  597. 42:51And what it's going to do is it's going to try  building and deploying. Now the probability this
  598. 42:54is going to work the very first go by the way is  pretty low actually because we're not giving it
  599. 42:58any additional settings or anything like that. So,  I mean, I'm going to look for it, but I doubt that
  600. 43:02it's actually going to oneshot it. If it does,  I'd be quite surprised. Wow, that's so funny. It
  601. 43:06just did. Uh, that's hilarious. I wasn't expecting  that. I was going to expect communicating with an
  602. 43:10agent to get it done. But anyway, yeah, we just  drag and drop the folder in Endearing Salyaki.
  603. 43:14And as you can see, our whole website is up. It's  actually up on the internet now. It's not up um,
  604. 43:18you know, where it was before. So, I'm just  going to open an incognito window just so
  605. 43:21you guys are 100% confident that it is on the  internet. I just accessed this. Why don't I um,
  606. 43:26load this up on my phone, too. endearing. Okay.  And I don't know if you guys could see this,
  607. 43:32but like that's the website. It's just on my  phone now. It's on a totally different um you
  608. 43:37know device. So yeah. Hey, I'm uh Nick Sarif and  today I'm going to show you how to get a website
  609. 43:43up on the internet in like a 45 seconds flat. Kind  of neat, huh? So this is more or less going to
  610. 43:49be the approach that I'm going to use to push all  of our apps to production just because, you know,
  611. 43:52I don't want us to have to spend a ton of money in  order to like actually run server infer and stuff
  612. 43:55like that. But yeah, in general, like you know,  if you're using a predictable library like this,
  613. 43:59it's pretty straightforward. Obviously, not every  single time is going to go that easily. And I'm
  614. 44:03going to show you guys what like more complex app  pushes look like. In general, what I do now is I
  615. 44:07just give my agent um an API key to the service  like Netlify. And then I just say, "Hey, you know,
  616. 44:11push this." And then it'll actually go through  and then do all of the work. Um but hopefully
  617. 44:14you guys see how easy it is to oneshot a website  with Gemini 3.1 Pro. Cool. So that's how to design
  618. 44:20a website. The issue with websites is websites  are really simple. They have no authentication.
  619. 44:25They have pretty cool UX as you can see and you  can get progressively more complicated as the
  620. 44:29models get smarter. Um, but there's no like actual  like like security or or data transmission that's
  621. 44:34really required, right? There's no interactivity.  So when we migrate from uh you know websites to
  622. 44:41apps, what we need to do is we need to understand  a couple things about security. And if we don't
  623. 44:47understand things about security, what'll end  up happening is the same thing that happened to
  624. 44:50some pretty popular libraries. You guys might be  familiar with like OpenClaw pretty recently or a
  625. 44:54Claudebot is what it was called before its 40th  rebrand. And the reason why part of the reason
  626. 44:58why I rebrand it so much is because there's just  so many security problems with it. Like people
  627. 45:01had 25,000 API keys leaked. API keys being like  basically the equivalent of like a password to
  628. 45:06a service. That's pretty important. Uh not to  mention, you know, API bills that were run up
  629. 45:10because hackers and stuff like that got access to  it. Or just like leaked data from users that use
  630. 45:16a specific thing. Never a good situation to be in.  So, I don't want to pretend like I can solve 100%
  631. 45:21of all security wos for you. I can't. The reality  is everything on planet Earth is hackable. It's
  632. 45:26just a question of how hackable. And the whole  idea of like 8020ing security is just to get
  633. 45:32your point get to a point where your app is less  hackable than the amount of effort that it would
  634. 45:37require to do it. And so almost like anybody  could theoretically break into anybody's house,
  635. 45:43but we don't because there's just like a little  bit more effort is required to like, I don't know,
  636. 45:47break my window than just walk into my front door.  Um, if you just like do some 8020, I don't know,
  637. 45:52put a fence in, have some camera outside your  front door or something, you'll eliminate the
  638. 45:55vast majority of like lowhanging fruit. Okay,  so I just want to run through the 8020 here. 80%
  639. 46:01of security problems in vibecoded apps will come  from five things. The first is exposed environment
  640. 46:06variables and API keys. The second is missing or  broken rowle security RLS on your database. The
  641. 46:12third is no server side validation which is  where you trust the front end for all of the
  642. 46:16validation steps. So verifying that a password  is a password and email is an email. Verifying
  643. 46:20your logic and your math and stuff like that. The  fourth is using outdated or hallucinated packages.
  644. 46:25Very important. And the fifth is not having what's  called proper authentication middleware. Now again
  645. 46:30you don't need to be a computer programmer to get  all this stuff. I'm going to explain it while we
  646. 46:33talk about it. What's really important is when  you actually go through and develop, you know,
  647. 46:37like a like a database for the most part, you just  like click the RLS button. Um, when you set up an
  648. 46:43app, you just tell Gemini 3.1 Pro High or, you  know, Claude, hey, you know, I don't want you
  649. 46:48to do server side validation. What's important  is that you just have it run through all of its
  650. 46:52packages afterwards or say, hey, do we have proper  authentication middleware on every page? You know,
  651. 46:57hey, are our environment variables and API keys  exposed publicly? And so I guess what I'm trying
  652. 47:02to get at is it's actually not that difficult to  like hit the AD20. You literally just like create
  653. 47:05one prompt and then you just feed it in as sort  of like a postbu workflow similar to what I showed
  654. 47:10you with the code review initially. So we can just  pass all the stuff in as a prompt and I'm going
  655. 47:14to do that and give you guys the prompt later and  it'll do pretty good. But obviously you know it's
  656. 47:19not perfect. No security ever is. This should just  allow you to launch apps without feeling like a
  657. 47:22fraud or needlessly endangering other people's  credentials. So let's chat about the first
  658. 47:26which is environment variables and then secret  management. For those of you guys that don't know,
  659. 47:30in computer programming, you typically have to  deal with the equivalent of a password. And so
  660. 47:34we call these passwords various things, tokens,  authentication credentials, environment variables,
  661. 47:38API keys, whatever. But they all sort of like come  to the same idea, which is that it is something
  662. 47:43that if uh a user has access to it, they can  typically access a bunch of features of their
  663. 47:49account and not somebody else's. And so the issue  with vibecoded apps is a lot of people with their
  664. 47:55agents actually hardcode authentication tokens  and secrets and environment variables into their
  665. 48:02code. And the way that I see it is this is kind of  like putting a sticky note with your password on
  666. 48:06the front of your monitor like you see in a lot of  like older school cubicles where it's like Gmail
  667. 48:10password 1 23123 Nick is super sexy.com whatever  and like anybody that walks by will see that and
  668. 48:17they will know your password. It's kind of like  that with um exposing environment variables and
  669. 48:22secrets inside of like a a front end. So, also  a lot of hackers will go through the website and
  670. 48:28app code and then just look for hard-coded  mentions of a specific string like next_pub
  671. 48:32uh you know whatever key or secret key or what and  that's a common string prefix. And what I mean by
  672. 48:37that is like you know if you load up the website  that we just had a moment ago which I don't
  673. 48:40actually remember the password I don't actually  remember the thing. So one sec. Yeah. Yeah. So,
  674. 48:44if you go through this website, we can actually  like right click, we can press inspect. And uh
  675. 48:47as we scroll through, we'll actually be able to  like command F different elements on the page. So,
  676. 48:52weaponize, for instance, is actually like  written in the code of the page. I guess you
  677. 48:55guys can't see cuz my fat head is in the way.  You guys see how down here I just command F
  678. 48:59weaponize and then we actually found the specific  segment. What if we do personalization? Right,
  679. 49:03that's there. How about initialize sequence when  I'm selecting this element? So what I mean by uh
  680. 49:09exposing your credentials is basically a lot of  the time somewhere on the front end people will
  681. 49:13write code so that when you click the map growth  button up here which we just found down over here
  682. 49:18um there'll be some additional thing like like  I don't know on click equal and I don't even
  683. 49:24remember like the actual function definition  for this but uh whatever you know fire my API
  684. 49:29key you know to whatever the website is and  then I actually like expose my API key which
  685. 49:36is right over here and so basically we is we just  want to avoid situations where I actually have,
  686. 49:41you know, on click fire my API key to this  location and here it is in plain text. Um,
  687. 49:46we also want to avoid the loca uh situation where  you have something like next public key equals
  688. 49:52whatever because if you have either of what I just  mentioned, somebody can just go on your website
  689. 49:56and then do the equivalent of like a command F  or control F and just type in like next public
  690. 50:00key and then they'll find something. It's really  dumb, but um you'd be surprised at how many really
  691. 50:05like high-profile libraries it's happened.  That's one of the issues that I've had with
  692. 50:08uh well anyway I'm not going to name any specific  names but yeah I've had some issues with some some
  693. 50:12recent vibe coded products because of this. So  what do we do instead? Well basically you put
  694. 50:16them in a file like av and then you just reference  them using imports or you tell the model like hey
  695. 50:20you know I want you to look in the specific place  for all of my API keys and credentials. And so if
  696. 50:24I show you guys a practical example just using  you know anti-gravity basically what you do is
  697. 50:28somewhere in the core of this you'd go env uh key  and then it would look like this and then no like
  698. 50:36um anthropic private key and then it would look  like this right and so basically what you do is
  699. 50:42you'd say hey what's my um enthropic key and uh  if you ever needed to use it to like construct
  700. 50:49something the model would instead of looking  through your your code base here and finding
  701. 50:53it like just written directly in a codebase.  It would do like a command f through the entire
  702. 50:58thing. It'd look for something like an enthropic  key or something like that and then it would go
  703. 51:02and it would actually find that it's 3 if4 and as  you can see it's analyzing the specific file to do
  704. 51:06so. So this is just like a programming convention.  Just keep all your passwords everything like that
  705. 51:09inside of av. Another benefit is you usually  don't push keys to like an a repository on the
  706. 51:15internet. Normally you just keep that locally on  your computer and then you give that to whatever
  707. 51:18like the app user or whatever to upload their own  keys. Pretty simple stuff. Not rocket science. The
  708. 51:22issue is just nobody actually does this. Nobody  actually asks their agent to make sure that all
  709. 51:25this stuff is done. The second is this idea of  rowle security. So um as you guys are going to
  710. 51:29see in the next project, we're going to use a  database and the database that we're going to
  711. 51:32use is going to called superbase. It's very very  popular with most vibe coder projects right now.
  712. 51:36And basically it's like the single most important  security feature on planet earth. But um you know
  713. 51:40these databases out there just don't enable this  by default because it's just not something that
  714. 51:45you know is enabled by default. I don't know.  I'm not a super in-depth computer programmer.
  715. 51:49but it changes a couple of things and some people  don't want to use a database like that. Basically,
  716. 51:53what this means is if you don't have this  feature enabled called RLS, anybody who has
  717. 51:57the Superbase URL and then what's called the anon  key, which is public by design, can read, write,
  718. 52:01and delete every single row in your database. And  that's just how Superbase works by default. And so
  719. 52:05some very popular vibe coded projects here did not  have level security. And basically anybody that
  720. 52:09signed up for them was given a key, sort of like a  password, and then they just use that password to
  721. 52:14search up all of the data about every other person  on it. And that led to like a massive massive,
  722. 52:19you know, issue. Try not to swear in these  videos, but it was a cluster. And uh, you know,
  723. 52:24that ended up with people's ability to delete  rows and databases, which was stupid. All RLS's.
  724. 52:30Basically says like, hey, user A can only see user  A's data. User B can only see user B's data. Like,
  725. 52:36obviously, it's not rocket science. Uh, but if you  just turn this on, you'll fix like 90% of errors.
  726. 52:40Okay, so 83% of exposed superbased databases  involved RLS misconfigurations. uh 83%. That
  727. 52:46means like only 17% of exposed superbase issues  were not related directly to this one thing that
  728. 52:51I'm telling you about that is basically just a  button. So we're just going to click enable and
  729. 52:54it'll be fine from now on. But just make sure to  know RLS is like the main lowhanging fruit. Next
  730. 52:58is something called serverside validation and um a  big problem with that is like you know how we just
  731. 53:03developed a website, right? Well, let's say on  their website there was some form and the form was
  732. 53:07um I don't know it was like a sign up form and it  said you know enter your email here and then enter
  733. 53:11your password and then let's say obviously in  order to implement any sort of sign up mechanism
  734. 53:15what we kind of have to do is we have to check to  see does the email already exists in our database
  735. 53:18and so what the server side thing what the front  end thing would do is it would basically say okay
  736. 53:23let's match the email to something in our database  well um when you do this sort of ser uh front-end
  737. 53:28validation where you validate like all of the  logic on your on your website um it's massive
  738. 53:34security risk because as you just saw a moment  ago, anybody can jump into the code of any website
  739. 53:38and then immediately change it. Like I could  go to google.com and then I could, you know,
  740. 53:44um hold command shift C or rightclick and then go  inspect element and then I could select anything I
  741. 53:50want on the page like this Google search button.  Then I could actually change it from uh I don't
  742. 53:55know this input class which is called Google  search and I could change it to nick search.
  743. 54:01And now I've just changed Google's website, right?  Accordingly, what I could also do is if there's
  744. 54:05some form here when I put my information in that  does my email or whatever, I could actually like
  745. 54:10have it go through a bunch of email addresses or  a bunch of passwords and then it would change the
  746. 54:15email and password that is being done the valid  accordingly. If I had a forum and this forum,
  747. 54:20you know, was like checking emails or checking  passwords or something, I could actually go
  748. 54:23through and then I could like see the data, see  the function that is actually doing the checking
  749. 54:26and then I could like look at it and I could be  like, wow. So the logic that that guy is using
  750. 54:29to check if passwords exist is he's checking to  see if it's over uh I don't know three characters
  751. 54:34and the maximum password length is 10 characters.  That means that uh you know I could theoretically
  752. 54:39enumerate through all passwords between three  and 10 characters and then I'd be able to find
  753. 54:43out anybody's password. You know it's like this  just gives attackers way too much information.
  754. 54:47Likewise, it also allows them to do things like,  you know, if uh a specific email address already
  755. 54:52exists in the database, what you could do is you  could use that same email address, but you could
  756. 54:56change the request that's being sent. You could  sign up a million different email addresses using
  757. 55:00some script. It's just not very scalable, I would  say. Um, and it's not very intelligent to do. So,
  758. 55:06instead, what we do is we actually do server side  validation. And what that means is like basically
  759. 55:10we have our site right over here. And our site in  general communicates with some server. And instead
  760. 55:17of doing all the validation over here, okay,  what we do is we say, "No, what I want to do
  761. 55:23is basically every time somebody tries to create  a new account, I'm not actually going to check
  762. 55:26on the site. What I'm going to do is I'm going to  send a request over to another backend somewhere,
  763. 55:29some server. The server is going to be much more  secure. And then because it's not on the site,
  764. 55:34nobody can like jump into the server and then  make minor changes to, you know, check out the
  765. 55:38logic and stuff like that. The only thing that  an attacker would actually ever see is just the
  766. 55:42fact that, oh, the site sent a request to the  server. uh but you know the server is like super
  767. 55:46password gated and you know requires specific  authentication. It's not anything that you know
  768. 55:50a person could actually use. So that's kind of  easy. You just ask your AI model, hey you know
  769. 55:54make sure to server side validate everything. Hey,  is anything here not being serverside validated?
  770. 55:58Okay, we'll make it serverside validated. And that  takes me to number four, which is dependency and
  771. 56:01package security. Um so when AI generates code,  sometimes it references packages that don't
  772. 56:05exist as in your AI will literally just make up  a package name. In case you guys didn't know what
  773. 56:09packages are. Basically inside of most folder  most coding uh projects nowadays you have like
  774. 56:13a node modules folder or something. And these are  all the services that this um repository is using
  775. 56:19in order to like build my website. And so it's  using witch word zod yto q prelude puny code
  776. 56:26react and so on and so forth. And so as you can  see like most websites nowadays are actually like
  777. 56:30very very heavily based on pre-existing libraries  that other people have built which kind of makes
  778. 56:34sense cuz like you know the longer the internet's  around the more people have built libraries that
  779. 56:37handle specific features and like obviously you're  going to want to just use somebody else's solution
  780. 56:40rather than build your own wheel and so that's  what a lot of people here are doing. Tailwind
  781. 56:44CSS for instance is a big design library that just  does a lot of the design for you. Arg parse just
  782. 56:48handles arguments and it's like a simple and easy  way to you know do bash scripts and functions.
  783. 56:53And so the issue is AI just came up with all  this stuff, right? But sometimes it'll actually
  784. 56:58download or it'll create a name of a module that  doesn't actually exist. So for whatever reason,
  785. 57:04I mean the training data or whatever or  just because of the way statistics works,
  786. 57:08maybe it'll create a folder here or uh whatever  called acorns and it'll try and download a library
  787. 57:13called Acorns and it turns out the library it  wanted to download is actually called Acorn, but
  788. 57:17instead it tries downloading Acorns. Now, people  that have done a lot of stat stats and stuff like
  789. 57:21that have like done a lot of this to see, you  know, what libraries the um AI models typically
  790. 57:26screw up on. And so, if it sees like, oh, you  know, this always says acorns instead of acorn,
  791. 57:31what it'll do is it'll actually these attackers  will go through and they'll make a big list of
  792. 57:35all these fake packages. And then they'll actually  create packages on the internet that correspond
  793. 57:40to these. And then these packages will just be  malware. So, instead of you downloading Acorn,
  794. 57:45now you're downloading Acorns. instead of it  being empty and being nothing because it's fake,
  795. 57:49now you're downloading somebody's package that  actually has like a string in it that says, "Hey,
  796. 57:53you know, when you download this package, I want  you to send all of the API keys to this service."
  797. 57:57They as like, "Oh, yeah, that makes sense. I'm  downloading this package. This package is legit.
  798. 58:01Let's do it." And then it sends all the API keys  to the service. So, I mean, like in practice, it's
  799. 58:04not anywhere near as big of a deal as just like  server side validation um issues or RLS, but yeah,
  800. 58:10I mean, like it can be a problem. Another issue  is AI will typically download like older versions
  801. 58:14and stuff like that if it's not constantly  instructed not to which means you might be
  802. 58:18pulling in a package with a security vulnerability  that you know actually got patched months or years
  803. 58:22ago. So in general the recommendation is ensure  you get the most updated packages as possible
  804. 58:26as opposed to like you know older ones. And then  finally this authentication middleware bit. Um in
  805. 58:31case you've ever accessed like an authenticated  service before typically the way that it works
  806. 58:35is you'll have some thing. So I'm just going to  open up a new thing and I'll go cloud.ai. Um,
  807. 58:40I don't know, slashnew. When I click on this, do  you notice how it just immediately jump me back
  808. 58:45to sluggin? Claw. New is like how you make a new  thread, right? Well, there are some apps out there
  809. 58:51where you'll pump in like claw.ai/ um I don't  know, maybe chat or something like that. Okay.
  810. 58:58And then basically you'll be able to act despite  the fact that you're not logged in, you'll be
  811. 59:02able to access chat if you just know that like  the URL is chat. Now obviously these guys are a
  812. 59:07major billion dollar maybe even trillion dollar  company by now. So every time I try and access
  813. 59:11this it immediately jumps you back to login. But  this is behavior that is handled by this thing
  814. 59:15called authentication middleware where basically  when you try and access routes that aren't your
  815. 59:18routes okay like settings and general and new and  and chat u it just knows that okay well you're not
  816. 59:24actually logged in so I can't show you that. I  need to get you back to the login page first.
  817. 59:27And so you know poor app design includes people  forgetting to put in authentication middleware um
  818. 59:32and then people have the ability to access pages  they shouldn't. And then sometimes it like allows
  819. 59:36them to manipulate things, rack up API usage uh  calls and stuff like that. So you can fix this by
  820. 59:42just ensuring middleware secures all routes. Okay,  so like I didn't want to make this little module
  821. 59:46here because it's boring as hell, but just know  that you know most people that build vibe coded
  822. 59:51apps will miss one of these five features and  then vibe coding in general just gets a really
  823. 59:54bad name because people just don't secure their  [ __ ] right? The reality is like nothing is 100%
  824. 59:58secure as I said, but if you just do these five  things and then um you know ask your AI models
  825. 1:00:03to fix them, uh you know, it'll do a reasonably  good job and I'd say about 80% of your security
  826. 1:00:07issues are going to be handled, especially that  rowle security thing. So what I've done is I've
  827. 1:00:11actually gone through and I've created a massive  prompt for all of you guys that you can use
  828. 1:00:14right over here. It's called the security audit  prompt. You just copy everything below this line,
  829. 1:00:18okay? And what you do is you give it to your model  and you say, "Hey, you know, I want you to check
  830. 1:00:23to see if all of this stuff is done." Then after  you're done, um, you know, flag all of your issues
  831. 1:00:29and then ask me what you want me to do about all  these issues. So, hypothetically, I mean, I'm just
  832. 1:00:33going to paste this whole prompt in, and I just  did to our website. Um, the issue with the website
  833. 1:00:38is obviously there's no real authentication going  on, right? So, it's not like it really matters too
  834. 1:00:42much. Uh, but still, you know, it's a reasonable  way for us to at least run through this. And now,
  835. 1:00:47uh, Gemini 3.1 Pro High, and I always recommend  using the smartest model for this stuff, is now
  836. 1:00:51just going to like take this prompt, pump through  literally everything, and then just say like,
  837. 1:00:54"Hey, this is good. Hey, this is bad. Hey, this  is good. Hey, this is bad." And then we're going
  838. 1:00:58to secure it by basically just saying, "Okay, fix  everything that's bad." Okay. And now it's given
  839. 1:01:02us a big returned checklist. It's saying that the  codebase is a classic static front end. Here's
  840. 1:01:08the systematic audit. No hard-coded secrets, no  API keys, and so on and so forth. No git ignore,
  841. 1:01:15which is something that they typically recommend  to um prevent you pushing yourv, no console log
  842. 1:01:21statements, you know, a bunch of things. And it  looks like, you know, we didn't actually have
  843. 1:01:25any to go off of for most of this. If you scroll  all the way down, it'll actually show you like
  844. 1:01:29here's the big checklist summary. Uh because this  isn't an app with any authentication, right? So,
  845. 1:01:33it's just like a website. And so, because of that,  only these checklist features are the only things
  846. 1:01:36that are relevant. But we did fail two. So, I'm  going to say is fix the two that failed. And then
  847. 1:01:43uh it's just going to go through. It's going to  add the git ignore. It's going to add a couple
  848. 1:01:45other things. You know, this takes time, right?  I mean, it it's going to take me some token costs
  849. 1:01:49as well. I'm going to spend some money on this  essentially. So, unsurprisingly, people don't want
  850. 1:01:52to do this and uh that people typically forget  it. But, you know, this is an 8020 pass. It's
  851. 1:01:57not going to fix everything, but it's going to fix  the low hanging fruit, which is to be honest what
  852. 1:02:01most people really just care about. When you vibe  code an app and you publish it and then it starts
  853. 1:02:05scaling and you start making some money from it  obviously then you can take some of that money use
  854. 1:02:08it to hire maybe an actual security engineer and  have them audit your project and stuff like that.
  855. 1:02:13Okay. And here you go. It did. So it updated this  to add the get ignore and then it updated this to
  856. 1:02:18um update eslint and resolve all four high high  severity mini match vulnerabilities which is
  857. 1:02:23cool. So yeah, looks like we are now solid. Let's  move on to something a little more interesting,
  858. 1:02:27which is taking everything that we now know about  how to build a beautiful front end and then how to
  859. 1:02:31do security audits and stuff like that and  then combine it into a full stack app. So,
  860. 1:02:36next up, we're going to build a fullyfledged  SAS app. The app that I want to build today
  861. 1:02:40is a client dashboard platform for a hypothetical  content writing company. And so, like any typical
  862. 1:02:47client dashboard, we're going to want to be able  to create orders, um, view pending orders. We're
  863. 1:02:52going to want to have like a nice sexy dashboard  which gives us an overview of everything,
  864. 1:02:56our stats and so on and so forth. Then we're  also going to want some sort of like settings
  865. 1:02:59or configuration page. Then on top of that, we're  going to need some sort of login naturally. And
  866. 1:03:04then I think at the very end, I'm also going to  produce a nice sexy landing page just to tie it
  867. 1:03:07all together. And then I'm going to push it uh  live to production as well, just so you guys could
  868. 1:03:10see how it all interacts. Before we actually do  the building, I just want to run you guys through
  869. 1:03:14what I consider to be the uh basically major vibe  coding design loop as of right now. And obviously
  870. 1:03:20there's a bunch of different ways to build apps.  And I don't want you guys to think this is like
  871. 1:03:24the the end- all beall. There are many many  different ways to do this. But in my experience,
  872. 1:03:28this is like one of the one of the good ones  right now. And if you follow this sort of flow,
  873. 1:03:32um you'll save yourself a fair amount of time  later on just in terms of like the design and
  874. 1:03:35then also security because um as I talked about  in the security module, there's a fair amount
  875. 1:03:40that goes into designing like a wellsecured  app. So the way that this works in general is
  876. 1:03:44we start with some sort of inspiration design.  And so there are a variety of different places
  877. 1:03:48you can go to for these inspiration designs, but  in general, I like going to um this website here,
  878. 1:03:53Dribble with threebs. I like going to this  one called godly uh website. And basically,
  879. 1:03:59there are a bunch of these sources on the internet  that compile really high quality designs. And like
  880. 1:04:04logically speaking, I'm not a designer, right? I  haven't spent all the time and energy necessary to
  881. 1:04:09know the right padding and the right color  schemes and all that stuff. So it's like,
  882. 1:04:12why would I worry about coming up with all that  stuff myself? instead I could just borrow somebody
  883. 1:04:16else's and then we can make some changes to it  and then once it's all changed and and and all
  884. 1:04:20nice and pretty. Um you know like we will have  taken the design fundamentals that somebody spent
  885. 1:04:25a lifetime putting together and then we could just  work off of that instead of spending god knows how
  886. 1:04:29long trying to figure out like the total amount of  margin on the left and the right hand side of the
  887. 1:04:33uh the elements. It's crazy stuff. So as somebody  that's like been doing a fair amount of design,
  888. 1:04:38I got paid for design. Uh it's not worth the time  and energy that it goes into learning all that
  889. 1:04:41stuff. So we start with an inspiration design. I'm  going to grab a couple of these. And then you have
  890. 1:04:46an optional step here which a lot of people are  starting to do now where you animate. So the idea
  891. 1:04:50is since Vibe coding now makes uh the ability  to like replicate designs and have high-end
  892. 1:04:54designs really really easy. You know you need  a way to stand out. And so the way that people
  893. 1:04:58are standing out now is through animations through  um like kind of videos that are playing. The idea
  894. 1:05:02being that you know a still can't make video based  stuff super super high quality. So you could still
  895. 1:05:06um stand out as like human created content or  uh designs with something like that. I'm going
  896. 1:05:11to show you guys how to do that. Anyway,  uh this does cost a little bit of money
  897. 1:05:14because there's some models out there that  you need that can convert images to videos,
  898. 1:05:17but I'll I'll run you guys through what that  looks like um for the landing page. After that,
  899. 1:05:20we need to build in the main functionality, which  is always going to be the dashboard. It's going to
  900. 1:05:24be things like, you know, your various widgets,  your various pages, and stuff like that. Then,
  901. 1:05:28we're going to do local testing and iteration.  Local testing, just so we're all clear,
  902. 1:05:32just means testing it on your device, and it also  means testing it with uh without a database. So,
  903. 1:05:36we're just going to do all the file and then, you  know, uh, data and stuff like that in like a JSON
  904. 1:05:41and then we'll just test it all locally, make sure  that it works. Once we've made sure that it works,
  905. 1:05:45we'll then push our data to a database. And then,  in our case, we're going to use superbase. I'll
  906. 1:05:49talk about that in a sec. But then, um, we'll  test it all basically with the database. Once
  907. 1:05:53we're done with that, then and finally then do  we create an authentication page. And I find um,
  908. 1:05:57doing O at the end is way better than doing O  at the beginning because if you guys remember,
  909. 1:06:00I mentioned like middleware, right? Well, like  a big issue with the middleware is you'll just
  910. 1:06:04like the low hanging fruit is you'll do the O  first, then you'll make the pages and then the
  911. 1:06:07O will only secure the first page that you do.  So instead, we're just going to do our O at the
  912. 1:06:11end and then the model will already have all  the context to like produce um you know good
  913. 1:06:15authentication middleware for all the pages and  then at the very very end we're going to deploy
  914. 1:06:19and then obviously the issue with you know testing  back here when it's sort of on your machine and
  915. 1:06:24then deploying is like you you need to test it  again. So we're going to do some end toend tests.
  916. 1:06:28We're going to do some miscellaneous designs and  I'll probably just throw in the landing page there
  917. 1:06:31since obviously the landing page doesn't really  have much functionality to speak of. And uh yeah,
  918. 1:06:35that's that's more or less the loop. And then  you know like when you're ready what you do is
  919. 1:06:38you just do the exact same thing. You just  make a new product and then you start with
  920. 1:06:41the inspiration design. Um you can do some video  animations if necessary main functionality local
  921. 1:06:46testing database testing off deployment and end  tests and then landing page. Then my inspiration
  922. 1:06:50design animate and so on and so on and so on  and so forth. So I do this on basically all my
  923. 1:06:54vibe coded apps and uh yeah works pretty well.  So the common vibe coding stack which I'm just
  924. 1:06:58calling the usual suspects here are going to  be a combination of Nex.js for the front end
  925. 1:07:02a superbase for the database and the off and  then some sort of serverless backend which
  926. 1:07:06um in our case is going to be netifi but you  can use netlifi versell and a bunch of these
  927. 1:07:10other tools but this is just what people mostly  use because it's just very easy to spin up. So,
  928. 1:07:14to make a long story short, in case you know, we  have people here that aren't familiar with the
  929. 1:07:17idea. Um, you know, when you sign onto a website,  obviously this is my really crappy rectangle. Um,
  930. 1:07:23and this is our browser with the three little  dots, maybe the URL bar and stuff like that. And
  931. 1:07:26you have like the app over here and I don't know,  some sidebar. And then here's some other stuff,
  932. 1:07:31you know, like what what you're seeing, what's  rendered here is is the front end. And um there's
  933. 1:07:37already different front-end languages, right? I  mean, like HTML is hypertext markup language. It's
  934. 1:07:41usually used to create the structure of the page.  If you have CSS, which is cascading stylesheets,
  935. 1:07:45that's usually used to like make the the  rendered elements really pretty. And then,
  936. 1:07:50you know, if you want functionality on top of  that, you will use JavaScript and, you know,
  937. 1:07:54TypeScript. And there's there's all these  different languages, right? Well, basically
  938. 1:07:57what happens is um using all these languages,  there's just so many different ways you could
  939. 1:08:01use them that all the developers were using them  slightly differently. Some were more efficient,
  940. 1:08:04some were less efficient. What people ended up  doing is they created uh front-end frameworks.
  941. 1:08:09Okay. Well, not even just a front-end framework.  NexJS is technically also like it's like a full
  942. 1:08:12stack framework but um they made frameworks which  just encapsulate all three of these into you know
  943. 1:08:18this thing next.js and so what this is this is  basically like a full way to manage your HTML
  944. 1:08:24CSS your JavaScript all these other programming  languages and then builds they build it in a
  945. 1:08:28very opinionated way that consistently produces  similar outcomes and you know follows a consistent
  946. 1:08:33and predictable pattern so that most developers  can just spin up a site really quick. This is
  947. 1:08:38doubly important in the age of AI where you know  when if things aren't standardized there's like a
  948. 1:08:42million billion different ways that an AI model  could make a site and because usually there's a
  949. 1:08:45lot less supervision when you're viing than um you  know like a traditional development process. A lot
  950. 1:08:49of these ways just like aren't really well thought  out. You know AI just picked the simplest lowest
  951. 1:08:53hanging fruit and went with it. So I recommend  using these frameworks and stuff like that just
  952. 1:08:56both to economize your work but also just to  make sites predictable. If you ever hand them
  953. 1:09:00off to anybody if you're doing these for clients  and stuff like that you know next.js is the way
  954. 1:09:03to go. Okay. So that's the front end. Um you know  Superbase is going to be our database. So, I mean,
  955. 1:09:07just think of it as like a big Google sheet with  like a bunch of different tables and columns. Wow,
  956. 1:09:11my drawing skills have gotten worse recently.  Uh, but to make a long story short, you know,
  957. 1:09:16the stuff that is visualized on our front end,  like our bar charts and our little widget apps and
  958. 1:09:20stuff like that. Obviously, we need to pull the  data from somewhere, right? So, it doesn't make
  959. 1:09:23sense to keep all the data like on the site cuz  it's always changing. What we do is we're going
  960. 1:09:26to pull from a database and then like use that to  actually go and and change features. Obviously,
  961. 1:09:31we're going to need a login screen, right,  with like a little user uh portal and then
  962. 1:09:35like a little password portal. Um, let's round  that off so it quits looking phallic. And uh,
  963. 1:09:41Superbase is going to help us with that as well.  And then finally, you need what's like called a
  964. 1:09:45backend, which is basically just like a server.  And this server is actually going to manage the
  965. 1:09:49interactions between our database, our front end,  our off, and and you know, a lot of stuff. So, you
  966. 1:09:54know, that's a little bit more cloud-based. You're  not really going to fully I can't really just draw
  967. 1:09:58something that makes sense there. But suffice  to say, all these four components are going
  968. 1:10:01to interact together really nicely. And then the  stack that basically all the tools use is Nex.js,
  969. 1:10:05JS superbase and then some sort of what's called  serverless um back end. Okay, so we could go
  970. 1:10:11into that or we could just build it and I'd much  rather just build it and then you guys could learn
  971. 1:10:14through the doing. So let's start with the very  first step which is finding an inspiration design
  972. 1:10:18and I'm going to immediately jump on dribble for  that. So dribble for those of you guys that don't
  973. 1:10:23know but just go on the website. It's basically  just a big list of like different designs that
  974. 1:10:27people have made and it's cool. It was it was  initially meant to be like a way for designers to
  975. 1:10:32create a portfolio and show off the work and stuff  like that, which is pretty neat. Now, you know, to
  976. 1:10:36be honest, I think a lot of people are just using  this to source AI designs. I don't know how much
  977. 1:10:39longer we're all going to have access to dribble,  but uh we'll see. And, you know, in our case,
  978. 1:10:44what we're looking for is we're looking for some  sort of like client dashboard, right? So, I'm just
  979. 1:10:48going to type client dashboard in here. Basically,  what you'll see is a bunch of people have created
  980. 1:10:52these really sexy client dashboards. So, I'm  just going to click on a couple of these. Um,
  981. 1:10:56yeah. So, I I already opened that one. So, let's  click on this. Let's click on that. This one's
  982. 1:11:01actually pretty nice. And then, hm, why don't I  open up? No, I don't really like that one. That
  983. 1:11:05one looks kind of dumb. This one here looks cool.  Okay. And as you can see, you know, I now have
  984. 1:11:10um like a list of, in this case, all clients on  the lefth hand side. You know, this sort of like
  985. 1:11:14nice gray pattern, and that's that's kind of cool.  I don't really like this one a ton, though. So,
  986. 1:11:18I'm just going to keep looking until I find one  that I really really like. Um, what you'll find is
  987. 1:11:22a lot of these are now videos as well. And there  are a couple reasons why they're doing videos. One
  988. 1:11:26of them is that they don't really like when people  screenshot them like I'm about to. That design's
  989. 1:11:31cool. Okay, this is reasonable. Um, this one's  pretty interesting. But the one that I initially
  990. 1:11:37picked that I just liked the look of was this  here, which is super simple and it's very like
  991. 1:11:43extensible and you guys can add on whatever the  heck you want, right? So, I think I'm going to
  992. 1:11:46use this. And uh, basically what we're going to  do is I'm going to create a screenshot of this
  993. 1:11:51and then I'm going to use the model to try and  replicate this as closely as humanly possible.
  994. 1:11:55And I have a prompt set up that I'm going to I'm  going to send it to and stuff like that. And then
  995. 1:11:58from this we're going to get like a really high  quality design. And then I think I'm also going
  996. 1:12:01to do the same thing for the landing page. Um you  know this design is different from this design but
  997. 1:12:06uh you know I'm just going to find a way to like  meld the two together. And then I think at the
  998. 1:12:09end we're going to have something that like has  the color scheme of this but it actually has like
  999. 1:12:13the design of this if that makes sense which is  ultimately what I'm going for. I like that design.
  1000. 1:12:16I like this um I guess this is sans ser but I  really like this font. So yeah let's uh let's
  1001. 1:12:21give it a go. So what I'm going to do first  is I'm gonna head over to anti-gravity. Okay.
  1002. 1:12:25And then I'm going to open up a new folder. And  I'm just going to call this full actually let's
  1003. 1:12:31go lowercase full stack client dashboard. That's  going to be my very uh first full stack app with
  1004. 1:12:38you guys. And then what I'm going to do first is  I'm going to talk a little bit about the different
  1005. 1:12:42types of models that we have available to us.  Remember how before we designed our landing page
  1006. 1:12:46entirely using Gemini? Gemini 3.0 Pro is awesome,  but personally I find that actual like system
  1007. 1:12:50plans and system designs are better done through  Opus 4.6 right now. So, what I'm actually going to
  1008. 1:12:54do is I'm actually going to do the planning in  Opus 4.6. I'll show you how to do that. First,
  1009. 1:12:58let me zoom in because this is pretty far out. And  then I'm just going to go to um plan mode here. If
  1010. 1:13:03you just keep on cycling through, eventually  it'll get to it. It's the one with the little
  1011. 1:13:05pause sign. And then I uh created a prompt here  that I just want to go through with you guys. So,
  1012. 1:13:10the prompt says, "You're a world-class website  designer with 15 years of experience designing
  1013. 1:13:14high quality, award-winning websites for Apple  and Dribble. We'd like to build a full stack
  1014. 1:13:18SAS client dashboard app for our content writing  business. It's very important that you get this
  1015. 1:13:22right. our career depends on it. This is a little  hack that I picked up from um I think it was like
  1016. 1:13:26a former OpenAI dev or something, but they found  that when uh you make it really really important,
  1017. 1:13:31like our career depends on it, the output quality  actually goes up just by a few percentage points,
  1018. 1:13:35nothing major. And my prompt is not winning any  awards here. So, uh anyway, I'll take every win
  1019. 1:13:40that I can get. As a client, we want the ability  to view all pending content orders and progress
  1020. 1:13:43in a beautiful dashboard. We also want the  ability to create new content orders using a
  1021. 1:13:47highquality but simple form. Let me just run this.  We want the ability to configure various settings,
  1022. 1:13:52modes, etc. And we also want anything else.  Your usual SAS app like this would include
  1023. 1:13:56the dashboard. SAS app should use superb. I said  superbase here. What I meant to say was superbase,
  1024. 1:14:00but I was using a voice dictation. So, what are  you going to do? Next.js and then tailwind.css.
  1025. 1:14:05And we will deploy using netlifi. I'll define the  UX via screenshots. So, don't worry about design
  1026. 1:14:11particulars. The flow will be first we'll build  the main functionality, which are the parts I
  1027. 1:14:15talked about above using a screenshot inspiration.  You'll take the design style from the screenshot
  1028. 1:14:19and then use it to build all of the signed in  pages. Then we'll make it interactive with local
  1029. 1:14:23data and ensure routes work. Then we'll add O and  DB with superbase. Then we'll make a landing page
  1030. 1:14:27and finally do an endto-end sweep to ensure  everything works including off, middleware,
  1031. 1:14:30security, testing, etc. Then deploy and retest.  Then I'm saying think extremely hard and generate
  1032. 1:14:35a great plan. Once you've developed one that is  comprehensive, report back here and I'll supply
  1033. 1:14:39some screenshots. That's how we can start the  design process. Okay, so I gave it a fair amount
  1034. 1:14:43of context and you can see it's already done some  thinking, right? put the text stack and looks like
  1035. 1:14:48it corrected my little issue there with superbase  phased approach right they want me to plan this
  1036. 1:14:52out comprehensively there's nothing in the current  um working directory so it looked it couldn't find
  1037. 1:14:57anything green field project and now it's actually  going to go and create the architecture and that's
  1038. 1:15:02what's that's what it's doing right now that's why  it's in plan mode now I should note here in the
  1039. 1:15:06bottom right hand corner you guys probably I don't  know if you guys could see that's pretty small we
  1040. 1:15:09got this little lightning um what I've done is  I've enabled this thing called fast mode just
  1041. 1:15:13because Opus 46 supports it and that allows it to  go two and a half times is faster approximately
  1042. 1:15:17for I think like 3x the price. So little bit of  an arbitrage there. Um I think the price is going
  1043. 1:15:22to jump up to 6x pretty soon. So it may not be  available when you guys are on it. But personally
  1044. 1:15:26I find for building really comprehensive plans  awesome tool and an awesome model. Okay. And
  1045. 1:15:31then uh basically what I wanted to do is I wanted  to like produce this big plan and then I'm going
  1046. 1:15:35to pass off this giant plan over to Gemini who I  think is actually just a better designer. Okay. So
  1047. 1:15:40once the uh thing is super comprehensively planned  um then I can just pass all this stuff to Gemini
  1048. 1:15:45with the screenshots. But sometimes claude code  will actually ask you or rather Opus 4.6 will use
  1049. 1:15:50cloud code to ask you questions and so that's  why I'm doing all this planning and stuff like
  1050. 1:15:54that here just in case it asks me some questions  for clarification. Okay. So I'm going to press
  1051. 1:15:58escape because uh it's basically like hey do you  want me to start? Then here it's going all the way
  1052. 1:16:04to the top here. We want to build a full stack  SAS dashboard. Here's the tech step. Here's the
  1053. 1:16:09phase one project setup in UI shell. And um I'll  be honest, like I'm I'm usually not reading this
  1054. 1:16:13entire thing. What I'm doing is I'm skimming.  I'm just making sure there's nothing that just
  1055. 1:16:16jumps out to me as stupid. Like what I want is I  basically just want to see, hey, are there way too
  1056. 1:16:20many pages? Is this way too complicated? Is this  model completely misunderstood what I want it to
  1057. 1:16:24do? And so what I'm seeing is there'll be like  an app page, there'll be um a dashboard page,
  1058. 1:16:30orders, a new page, a settings page, notifications  page, and that looks pretty reasonable, right?
  1059. 1:16:35There'll be a components page where it'll actually  store all the components. Library page. Okay,
  1060. 1:16:39this looks pretty good. This looks pretty  good. Interactive local data. So after that,
  1061. 1:16:44we'll define some types. Yeah, I don't even know  what the hell that really means to be honest, but
  1062. 1:16:47that's okay. And then we have those actual pages,  which look good to me. All of these are pages
  1063. 1:16:51that I would realistically want my app to have. Is  there anything else I'd want? H dashboard orders.
  1064. 1:16:55No, I think I think this is fine. After that, we  have the superbase off. So here, I'll like set
  1065. 1:17:00up the superbase, but that's okay. That's not for  now. That's later. We'll finally have the landing
  1066. 1:17:04page which is going to be really nice and sexy and  then we'll have some key architecture decisions.
  1067. 1:17:10Okay, cool. I mean, this seems pretty reasonable  to me. I don't think there are any problems
  1068. 1:17:13here whatsoever. So, what I'm going to do is I'm  actually just going to copy this whole plan. Okay,
  1069. 1:17:18this whole thing that this just created for me.  I'm going to paste it into this now. Okay. And
  1070. 1:17:24then I'm also going to provide some initial  screenshots of what I want the dashboard to
  1071. 1:17:27look like. So, I'm just going to command um you  know on a Mac you can command shift control. So,
  1072. 1:17:34command shift control 4 and then I'm just going  to go select this. Okay. And that'll actually
  1073. 1:17:40give me like a pretty high quality screenshot.  I'm going to feed this in. Okay. And so now we
  1074. 1:17:46have the image of the dashboard and then I'll say  design using this style as inspiration clean and
  1075. 1:17:53minimal. Okay. Okay. So, what I've done is I've  now split the work up between these two agents.
  1076. 1:17:58I had um Claude Opus 4.6 design me the really  comprehensive plan because as I mentioned I
  1077. 1:18:02think it's a little bit better at planning  at least as of the time of this recording.
  1078. 1:18:05Then I'm going to hand off all of like the design  and then you know basically just like grunt work
  1079. 1:18:11over to Gemini 3.1 Pro High, which I think is way  better at actually like wiring up the components
  1080. 1:18:15and then putting together like that that really  high class design. And uh you know at this point
  1081. 1:18:20all we really have to do is just wait for it to  build. And this is realistically because it is,
  1082. 1:18:23you know, going to be a pretty comprehensive app.  This isn't something that's going to happen in a
  1083. 1:18:27couple minutes. You're probably gonna be good to  like go step away, have a coffee, come back. By
  1084. 1:18:31the time all that stuff's ready, this will have  given you some sort of result. But it's always
  1085. 1:18:36good before you do that just to like wait for,  I don't know, 30 seconds or so because sometimes
  1086. 1:18:40it'll give you a plan and then you can just review  the plan um and just double and triple check that
  1087. 1:18:44it didn't do something super stupid or super  terrible. And I don't think it has. Everything
  1088. 1:18:48here looks good to me. So, I think it can just  go ahead and commence the project. Cool. So,
  1089. 1:18:54I'm actually going to go grab a coffee and I'll be  right back. Okay. So, now it's telling me it's now
  1090. 1:18:57completed phase 2 interactive with local data. So,  we should now have a site up and running with some
  1091. 1:19:01sort of local data. Immediately after I said let's  open it. So, it's opened it. I tried doing some
  1092. 1:19:06initial debugging and stuff like that on its own.  It it didn't end up doing so because there was an
  1093. 1:19:10additional error which I'm going to talk about.  And just on the uh I guess concept of errors
  1094. 1:19:15when you create a full-fledged SAS app like one  that has like back and forth and stuff like that,
  1095. 1:19:18not just a website where there's no interactivity,  you know, you're going to have errors. And so it's
  1096. 1:19:22not about like will I screw up at some point.  Will the model get this wrong? Just a matter
  1097. 1:19:27of when and then what you're going to do when uh  it screws up. So basically what I've done is it
  1098. 1:19:32started the development server and opened this in  my local browser. So I just click this open and
  1099. 1:19:36as you can see here we have the app set up, but  the app looks a little funky. We don't have any
  1100. 1:19:40styles. Just looks like crap. So obviously this  isn't what we want, right? What I'm going to do
  1101. 1:19:44instead is I'm just going to take a photo of this  and then I'm just going to send it back. And then
  1102. 1:19:47I'm going say I don't think styles are loading  also because I'm pretty sure there was some issue,
  1103. 1:19:53right? I initially got this problem as well where  it said missing HTML and body tags in the root
  1104. 1:19:57layout. So I'm also going to copy this in. Also,  I got this error. I'm going to paste that in. So,
  1105. 1:20:03you know, at least initially before you even  get to be able to play around with the UX,
  1106. 1:20:07you may have some like initialization problems and  config problems and stuff like that. And that's
  1107. 1:20:11okay. Basically, what you do, um, if I just show  you guys sort of how I think about vibe coding
  1108. 1:20:16these things is it's almost like I don't know,  you're in a cave. Uh, have you guys seen like the,
  1109. 1:20:22you know, mining meme where you're like mining  for gold? Okay, basically you're in a cave and
  1110. 1:20:27every single time you run the thing, you're like  this fella here. You just get a little bit further
  1111. 1:20:32and a little bit further and a little bit further  and you know this fell here can't see anything.
  1112. 1:20:38It's just darkness in front of him, right? So  every time he mines, he goes home and he's like,
  1113. 1:20:42"My god, I didn't make any progress today." But  obviously if he just continues going, eventually
  1114. 1:20:46he gets to the point where there's a bunch of gems  sort of on the other side. And so that's basically
  1115. 1:20:49what we're doing. We're just going to work through  this initial sludge with initialization errors by
  1116. 1:20:53copying and pasting um any problems and then just  giving it directly to uh the model until we get
  1117. 1:20:58to that little gold gem. Once we're here, we can  actually start making real changes to our app. Um,
  1118. 1:21:02and all of that is reasonably well expected. Okay,  speaking of which, it just modified some of the
  1119. 1:21:06CSS after I sent it this message. And as you  can see, we now have a little dashboard set up,
  1120. 1:21:10one on the left hand side. So, we've already made  some some reasonable progress. I'm just going to
  1121. 1:21:13dashboard, see if there are any issues. Okay, I'm  not seeing any issues at all. So, we have five
  1122. 1:21:16total orders, one in progress, two completed.  This is just some fake data made up. So,
  1123. 1:21:20you can see we can now mouse over each of these  three things or uh five things. SAS growth guide,
  1124. 1:21:25Q3 newsletter, so on and so forth. So, these are  all the orders that we have submitted as clients.
  1125. 1:21:30There's a little notification toggle. Um, if I  click on the orders page, we're now here. So,
  1126. 1:21:35you can actually see the orders better. I'm just  curious if I click new order, what happens? Okay,
  1127. 1:21:40so we're now on a new order page where I can  actually add info. So, I'm going to say this
  1128. 1:21:44is an example. New order, content type, landing  page. Hey, I want to build a really cool, sleek,
  1129. 1:21:50sexy landing page. And then, you know, I want some  stuff here. And then here's my requested deadline.
  1130. 1:21:57I don't know. We'll say March the 1st. We want  to add SEO meta tags and then require approval.
  1131. 1:22:02I'll click save order. Okay, cool. And it looks  like it's got the functionality. And so I can now
  1132. 1:22:06actually add orders. If I go to settings, what  do we got? Demo user, Acme Corp, email address,
  1133. 1:22:11cool preferences, email notice, weekly digest.  Okay, so these aren't working. At least the
  1134. 1:22:15weekly digest isn't. But that might be intentional  just because we don't have um access to, you know,
  1135. 1:22:20some sort of email. But yeah, I mean like to  be honest, like the the core functionality
  1136. 1:22:23of the app's already made. So although the  design is still pretty shitty, I would say
  1137. 1:22:27and obviously I'm going to want to fix that up.  Um core functionality is done. We basically have
  1138. 1:22:31like I want to say a REST API, but we have like a  little CRUD app here. We can create, we can read.
  1139. 1:22:36Um I don't actually know if we can update. Doesn't  look like we can go to the specific order page to
  1140. 1:22:41update yet. So maybe I'll make a note of that. Um  but we can presumably also Oh no, I don't think we
  1141. 1:22:46can delete either. Okay, cool. Anyway, this notice  page also has notice. That's kind of neat. Um,
  1142. 1:22:50I think what I'm going to do now is I'm just going  to voice dump in all of the problems that I see.
  1143. 1:22:54And then we're just going to go back and forth  until we can eliminate just the minor little
  1144. 1:22:58errors like styles and stuff. And then once we've  tested and confirmed the functionality here, then
  1145. 1:23:02I'm going to do a big stylistic upgrade. After  we've done the stylistic upgrade, I will uh then
  1146. 1:23:07make this database friendly. And then once it's  on the database, then we can actually push. Hey,
  1147. 1:23:11this is really well done. Nice job. When I click  on a new page, there's initially some there's a
  1148. 1:23:17there's a brief initial load where it says loading  orders or loading settings or a loading dashboard.
  1149. 1:23:23I'd like you to remove that. I don't want any sort  of loading um widget here because it just makes it
  1150. 1:23:28look lower value. Instead, I want you to maintain  the structure of the page and just leave all of
  1151. 1:23:33the various sections blank. So, for instance,  if I were to click on orders, rather than it say
  1152. 1:23:39loading orders before it populates the rest of the  page, uh where it shows me the table and stuff,
  1153. 1:23:43I just want you to present the table to me  immediately and then just leave it blank. That
  1154. 1:23:47way, we could fill in the text um afterwards. Um  right now the navigation text is in light gray.
  1155. 1:23:58I'll take a screenshot and I'll show you what  I mean. But on the orders page, for instance,
  1156. 1:24:03um the text that says orders at the top lefthand  corner is very similar to the background color.
  1157. 1:24:08So that's annoying. I'd like some sort of graph  on the main dashboard page cuz right now I don't
  1158. 1:24:12have any. I'd like a way on the dashboard page  to click into the recent orders as well. Uh
  1159. 1:24:16right now I am capable of mousing over them and  something changes, but it's just a style effect.
  1160. 1:24:21I actually want the ability to click on them. In  addition to being able to create, I also want to
  1161. 1:24:25um be able to click on each individual article  on the orders page and then view it. Right now,
  1162. 1:24:31when I click view, it says either order not found  or it takes me to some error page, which is not
  1163. 1:24:38what I want. The notifications page has a mark all  red button that is currently grayed out. When I
  1164. 1:24:44click on the notifications at the top right hand  corner, that little icon, nothing happens. So,
  1165. 1:24:49I'd like that to just take me to the notifications  page. There's also nothing that happens when
  1166. 1:24:52I click on my little profile picture in the  top right hand corner. Under settings, when
  1167. 1:24:58I toggle weekly digest, nothing happens. Email  notifications works, but the weekly digest toggle
  1168. 1:25:03doesn't. There's a nextjs error here called param  property was accessed directly with params.id.
  1169. 1:25:09Params is a promise and must be unwrapped with  react use before accessing its own properties.
  1170. 1:25:14Nothing happens when I click on the little demo  user button in the bottom lefthand corner either.
  1171. 1:25:20This is quite a promising start. We just have  a few adjustments that we have to make. Uh so
  1172. 1:25:24that functionality is perfect. Once you're done  with that, let me know and then we can proceed.
  1173. 1:25:28Cool. So I've just added all this context and  I'm just going to take a screenshot now of that
  1174. 1:25:32issue that I talked about where the orders  text was um you know kind of gray. That'll
  1175. 1:25:38provide some more context. I'm keeping this small  intentionally because every new pixel is like
  1176. 1:25:43more tokens than I'm consuming, right? There's  some other minor stylistic changes and stuff,
  1177. 1:25:47but for now I'm not going to worry about the  style. And the another reason why is because
  1178. 1:25:50um once you have an app that's like up and running  like where all the functionality is right then you
  1179. 1:25:54can just like open a new Gemini instance and not  have any context and then just say like hey here's
  1180. 1:25:58my app I just want you to change a design and then  it can just go into the style sheets and stuff
  1181. 1:26:01like that make it really sexy. Uh whereas if you  try and mix all of this stuff into one big long
  1182. 1:26:06context window sometimes it can get messed up. So  you know I just want this specific chat right now
  1183. 1:26:11to focus on the main functionality and then we  can worry about the design afterwards. Anyway,
  1184. 1:26:14let me just make sure I didn't add in any  additional information. Cool. Cool. That looks
  1185. 1:26:18good. Grade out. Okay. Why don't I do this? There  you go. Cool. So, now deliver that information.
  1186. 1:26:26And just like um last time, uh I'm just going to  sit tight and wait for it to relaunch. Okay. It's
  1187. 1:26:30telling me that it's now updated everything.  I'm just going to click accept all. And then
  1188. 1:26:33we'll go back to the specific page. Let me click  on settings. Cool. We don't have any issues there.
  1189. 1:26:38Um everything there looks fine. Oh, you know, I  think there's one thing I forgot to point out,
  1190. 1:26:43which is this um notifications button. I think  that's going to be okay because we're probably
  1191. 1:26:47just going to massively change the style here. But  yeah, that looks fine. Let's actually click on a
  1192. 1:26:51specific order. Nice. This is now pushed all the  way to the left. The order um arrow looks really
  1193. 1:26:54nice. I don't know if there's a way for us to  uh mark this as completed now, right? Okay,
  1194. 1:27:00cool. It also says start work. That seems kind of  odd. I wonder why it says start work. Um yeah, I'm
  1195. 1:27:05noticing that as well. So, I think we're probably  going to have to remove that. The model might like
  1196. 1:27:08fundamentally misunderstand what I want. What I  basically want is I just want the client to have
  1197. 1:27:11like a dashboard where they could see it all. Hey,  I'm noticing there's like a start work button. Um,
  1198. 1:27:16just to be clear, this is a dashboard for a client  to look at the work that is currently being done
  1199. 1:27:21by the agency. So, they don't have the ability  to start work or anything like that. Just go
  1200. 1:27:26through and fix this. So, if there are any other  idiosyncrasies, um, those are taken care of. Okay,
  1201. 1:27:30cool. We got that last change here. And it looks  like everything is now super clean. Um, no major
  1202. 1:27:35issues whatsoever. If I click on this button,  uh, we only have readon access. Essentially,
  1203. 1:27:40clients can't make any changes. they can only  download stuff and the HC is what initiates that.
  1204. 1:27:44So that's what I wanted. From now on, what we're  going to do, rather from here on, what we're going
  1205. 1:27:47to do is we're going to redesign this because  I think the design is kind of elementary at the
  1206. 1:27:50moment. And I'm going to use that same approach  that we talked about earlier. We're going to find
  1207. 1:27:53a really high quality pre-existing design and I'm  going to have Gem and I basically go through and
  1208. 1:27:57then modify this to match. Um, and the idea is it  should be able to modify this to basically be like
  1209. 1:28:01almost pixel perfect. Uh, we're just going to like  change the fonts and stuff like that. Okay. So,
  1210. 1:28:06I'm going to go through dribble again. And I mean,  I like this idea of like a light mode dashboard.
  1211. 1:28:11Uh, I really do. Uh, what we had before is kind of  mid. So, I don't want that. I do like the idea of
  1212. 1:28:19like something dark on the left hand side, though.  Kind of break it up a bit. So, I'm going to see if
  1213. 1:28:24I could find something that is dark. Let's take a  quick peek at this one. This one looks all right.
  1214. 1:28:30You know, I really, really like this one. This  one looks super clean. Check that out. Okay. So,
  1215. 1:28:34I'm a big fan of this. Super big fan of that. I  think what I'm going to do now is I'm going to
  1216. 1:28:39take this screenshot. Okay, copy that in. And then  I'm going go back to Gemini. I'm going to paste it
  1217. 1:28:46and I'll say, "Hey, this is great. I'd now like  to change the design significantly. You should
  1218. 1:28:51do the vast majority of your work in Tailwind  or whatever stylesheets that you're currently
  1219. 1:28:55using to build this." Um, in short, I think the  design right now is very basic and super simple.
  1220. 1:29:01I want you to add significantly more  complexity um using things like cool
  1221. 1:29:06mouseover effects on navbar elements on the lefth  hand side. I want you to add really highquality
  1222. 1:29:12icons. I'd like you to modernize the design  significantly. I want you to try different fonts,
  1223. 1:29:17higher quality fonts. I want you to use like  cutting edge um new ones that are on Google fonts,
  1224. 1:29:23etc. I want you to use some placeholder images  so that the design feels alive. And I also want
  1225. 1:29:28you to significantly upgrade the graph. What I've  done is I've given you a screenshot from a similar
  1226. 1:29:33design that I like a lot and I want you to mimic  more or less everything that you see here just as
  1227. 1:29:38a uh just as a start point. I'll modify the design  slightly afterwards, but try and really nail the
  1228. 1:29:46font colors. Uh try and mimic the font styles. Try  and mimic the um encapsulation, the border styles,
  1229. 1:29:53cards, etc. Okay, this is looking a lot cleaner.  I'm loving how it did this design. You also see
  1230. 1:29:59way higher bar charts, way cooler bar charts. Um,  this takes me to what looks like a mini landing
  1231. 1:30:04page that I put together. That's interesting.  I wasn't even like looking for a landing page,
  1232. 1:30:08but it's nice that it did. So, and we even have  like a little look at that. It's like a little
  1233. 1:30:11notion um avatar up top. Cool. Um, my tasks  are still the same. When I click this button,
  1234. 1:30:16you see we do have that higher quality design,  which is nice. And nothing pops up for calendar.
  1235. 1:30:22Nothing pops up for reports. Nothing pops up for  portfolio. Nothing pops up for these buttons.
  1236. 1:30:27Neither does it pop up for those buttons. Let me  just check the bottom. Okay. And then yeah, the
  1237. 1:30:31settings work. So, basically, it's just populated  this with a bunch of additional buttons that we
  1238. 1:30:34don't need. I'm just going to tell it to remove  all the stuff that we don't need. And then I'm
  1239. 1:30:37also going to have it adjust the font a little bit  cuz I think the font's the same. Hey, this looks
  1240. 1:30:41much better. Fonts are the same though. So, I want  you to adjust the fonts. Um, I'd also like you to
  1241. 1:30:47change all of the major titles from title case to  sentence case. For instance, task completion over
  1242. 1:30:54time should be sentence case. Apply this to all  other elements and boxes. I'm liking the design
  1243. 1:31:00quite a bit. Nice job on the avatars. I think  you should add borders rather than shadows around
  1244. 1:31:06things to better match the task beto design. I'm  also noticing that you put a bunch of additional
  1245. 1:31:11buttons that we don't need. Like for instance,  calendar, reports, portfolio, product management,
  1246. 1:31:15project management, real estate website, my first  portfolio, all team product team, invite team,
  1247. 1:31:21supports, that little thumbtack icon, the play  icon, the integrate icon. These aren't things
  1248. 1:31:30that we actually need because there's no pages  that will address them and I don't plan on making
  1249. 1:31:34them. So, I'd like you to remove all elements  for whom we don't have pages because that's
  1250. 1:31:38not really relevant. um make the search bar apply  to our current list of orders and then update the
  1251. 1:31:47design of the settings page because right now it  looks the same as it did before. And then finally
  1252. 1:31:52in inbox the button that says mark all as red  is um almost completely transparent. It's very
  1253. 1:31:58difficult to see unless you mouse over it. So fix  that as well. I think that's more or less the last
  1254. 1:32:03round of edits and then we can get into publishing  this. Cool. And this is the final result. I have
  1255. 1:32:07a very clean dashboard. You see with that scroll  on the right hand side, we don't have any issues.
  1256. 1:32:12Down at the bottom, we have only the pages that  are actually relevant to us. Now, of course,
  1257. 1:32:16I could add like a million pages here if I wanted  to, but I don't really. I mean, like this is just
  1258. 1:32:19the purpose of the app, right? I think in our  uh crazy vibe coded economy, you're going to
  1259. 1:32:24find that like a lot of apps are going to have  unnecessary features and whatnot just because they
  1260. 1:32:27can. I think simplicity is actually going to end  up being quite the moat. So, yeah, I'm going to
  1261. 1:32:31keep things as simple as humanly possible. Uh but  yeah, everything works, which is really nice. So,
  1262. 1:32:35you know, if I click on this app, uh, sorry, if  I click on this specific content page, you know,
  1263. 1:32:39you can see that I'm I'm here. Content's being  written and stuff like that. I don't have the
  1264. 1:32:42ability to modify like I had last time, you know,  I can download stuff if necessary. If I go back to
  1265. 1:32:46the dashboard, this um graph is interactive. Uh,  you know, and I I can jump into this anywhere I
  1266. 1:32:52want, which is kind of neat. And then down at  the very bottom, which you guys can't see cuz
  1267. 1:32:56my fat head's in the way, I have the settings  page, which is pretty neat. Um, and then, yeah,
  1268. 1:33:00we also have the ability to search tasks up here,  which is really, really cool. Um, I could type SAS
  1269. 1:33:05growth guide and then that's an initial piece an  additional piece of functionality that was added.
  1270. 1:33:10Okay, so I'm just going to clear that notif. And  now that we've like really basically built this
  1271. 1:33:14whole app directly on the computer, it's time to  take this to the cloud. So, what I'm going to do
  1272. 1:33:19next is I'm going to go to anti-gravity and just  before we proceed with our next step, I'm going to
  1273. 1:33:24ask it to save everything that it's done so far  into a gemini.mmd that effectively encapsulates
  1274. 1:33:30what this app is, everything we've done so far,  and then provides instructions for future models
  1275. 1:33:33in case we need to pass this off. And the reason  why I do this is because you might actually run
  1276. 1:33:38out of like context. Um, that happens pretty  often. For those of you guys that don't know,
  1277. 1:33:41there's only a certain number of tokens that you  can actually fit into one conversation with an AI
  1278. 1:33:45model these days. Whether it's like Opus 4.6  six with a 200,000 context window. They have
  1279. 1:33:50a 1 million context window option as well.  Whether it's, you know, Gemini 3.1 Pro high,
  1280. 1:33:54I think I think it has a 200k context window,  might have a million. The point I'm making is
  1281. 1:33:58like a lot of that context just used up by the  internal thinking of the model as it does tasks,
  1282. 1:34:02right? So, in my case, like I I just don't want to  risk it. I don't want to like get the thing to the
  1283. 1:34:06point where it's gone a little too far and then it  barely remembers what we talked about initially.
  1284. 1:34:10Instead, what I want to do is I basically want to  like have this almost like a backup of where we
  1285. 1:34:14are right now. This gemini.mmd file which uh you  know in my case is just a very highle summary that
  1286. 1:34:19talks about where we currently are in the process  and you know what we need to do and stuff like
  1287. 1:34:23that and then also gives instructions for you know  where to go from here. So once we're done with all
  1288. 1:34:29this and now we have this which is sort of like my  fallback what we can do is we can um move on with
  1289. 1:34:34the next step. So I'm going to say fantastic the  current design looks great. What I want to do next
  1290. 1:34:38is I want to ensure that it works not only locally  but with Superbase as our database. Walk me
  1291. 1:34:45through everything I need to do. In case you guys  didn't know, Superbase being our database. Um,
  1292. 1:34:49this isn't something the model can actually set  up entirely for us. Instead, what we're going to
  1293. 1:34:53do is I'm just going to ask it to walk me through.  And that's what it's done. Create a new Superbase
  1294. 1:34:57project up here. Set up the Superbase client  and so on and so forth. Create the database
  1295. 1:35:01schema. Enforce RLS. That's really important  like we talked about. Then replace hooks. and
  1296. 1:35:05we're actually going to have it do some of this  stuff, but we'll start with database.new. So, I'm
  1297. 1:35:09just going to jump over there. It'll now ask us to  create a new project. Now, in my case, I'm already
  1298. 1:35:13signed into Superbase. So, I can just click that  button and then boom, it's done, right? They own
  1299. 1:35:16the freaking domain name database.new. They got  a lot of this, right? And they've streamlined the
  1300. 1:35:21setup to match. But, uh, if you don't already have  a Superbase account, just open up an incognito
  1301. 1:35:25window and then just go to superbase.com and then  just click start your project in the top rightand
  1302. 1:35:30corner and then just enter your information down  over here. email, password, you can continue
  1303. 1:35:34with GitHub, SSO, whatever, and just make an  account. They're fantastic. This is like a really,
  1304. 1:35:38really solid app, and uh it simplified the  development of like vibecoded sites 100x over. So,
  1305. 1:35:44once you're done with that sign up, um you'll be  at a page like looks like this. I'm just going to
  1306. 1:35:47type I don't know, Nikki Poof. I really got to get  more mature names for these. Uh okay, why don't we
  1307. 1:35:55do I don't know. We'll just do client dashboard  app. Next up, we need a database password. So,
  1308. 1:36:02I'm actually just going to make like a my own fake  one and then I'm going to copy it over. Actually,
  1309. 1:36:07maybe we'll just generate one. The generated  one's weaker. So, I'm just going to copy that.
  1310. 1:36:12We'll enable the data API. This stuff looks good.  Then I'll click create a new project. Okay. So,
  1311. 1:36:16we have our database passwords right here. So,  just so that I don't lose this, I'm actually
  1312. 1:36:19going to give it the password right here. And  then I'm just going to have some additional
  1313. 1:36:24other lines. So, boom. It's now created the um  thing for me. And then I think what I do next
  1314. 1:36:31is I have to go to project settings. There's a  project ID over here. So I'm going to copy this
  1315. 1:36:36over and then I'll go project ID. Paste that in.  And then I need the superbase superbase URL as
  1316. 1:36:43well. So I don't actually know exactly what that  URL is, but I'm just going to copy the dashboard
  1317. 1:36:48name as well. So the project name, paste that  in. Let me just see if there's anything else.
  1318. 1:36:52Project URL and on public key. So I think we need  to go to API, which might be over here. API keys,
  1319. 1:36:58which is right over here. We're going to create  a publishable key. That's one that we want. And
  1320. 1:37:03then I'm going to copy this. And then I'll say  publishable key. I'm just going to paste that in.
  1321. 1:37:11Okay. So now this should be everything the model  needs. I'm not entirely sure. I think it is. So
  1322. 1:37:15we're just going to give it all that information.  We're going to have it do the rest of this for us.
  1323. 1:37:20Um and then cool. Looks like this is going to  take care of that. That's going to take care of
  1324. 1:37:24the database schema. Oh, sorry. We need to take  care of the database schema as well. So anyway,
  1325. 1:37:28I'm just going to give this its information and  then we'll have it tell us what to do next. And
  1326. 1:37:32now we'll have edited an ANEV file, which is  pretty clean. It's going through and it's adding
  1327. 1:37:36the information that we just gave it a moment ago.  And now what it's going to do is it's going to
  1328. 1:37:40give us what's called an SQL schema, which is just  like the next step. And I imagine it'll just ask
  1329. 1:37:44us to copy and paste something. It's also doing  things like wiring up the login and signup forms
  1330. 1:37:47to Superbase O, which is super cool. So I mean, we  should have basically everything good to go aside
  1331. 1:37:52from the landing page after this is done. Okay.  Okay. And then it's told us to go over here to SQL
  1332. 1:37:55editor and then paste this giant file in. Um, so  I just did that. Since these are comments, this is
  1333. 1:38:00just going to run a bunch of these simultaneously.  So I'm going to click run selected. Okay. And then
  1334. 1:38:03it told me to go over here and then paste all the  stuff in and then just press run. So that's what
  1335. 1:38:07I'm going to do. This will basically create us a  bunch of um tables and whatnot in our database.
  1336. 1:38:13So if I go to database now, we we're going to have  a bunch of different tables and they're all going
  1337. 1:38:16to connect in a specific way. And this is now  taking us to a signup page here. We obviously
  1338. 1:38:20still have some changes that we need to make.  So, I'm going to do that after I verify whether
  1339. 1:38:23or not this works. Now that it says signing up,  account created successfully. Please check your
  1340. 1:38:26email to confirm your account. I don't know if um  we're going to get that because sometimes we have
  1341. 1:38:30issues receiving emails. So, let me just pump  over to my own Gmail real quick. Okay. Yeah,
  1342. 1:38:34looks like we did. So, I can now confirm my  mail. Um that's taken us to I think like this
  1343. 1:38:38hastily putting together landing page, which is  not actually the page that we want. So, I'm going
  1344. 1:38:43to click sign in. And then I think my email was  this. I'm not entirely sure. And then my password
  1345. 1:38:48was that. Let's click sign in. Okay, cool. Yeah,  we actually did sign in. That's wonderful. Um,
  1346. 1:38:53perfect. Now we have this dashboard, which is  kind of neat. My tasks. Uh, cool. We can click
  1347. 1:38:57new task. Now we can create a new content order.  So, I'm going to go example content order. Make
  1348. 1:39:03XYZ. Cool. And then we may have to change the  order options here, too, cuz I don't think I uh
  1349. 1:39:09included that. Let's just select that. Click save.  Okay. Let's just make more characters. Okay. So,
  1350. 1:39:16there's some issue with the database because  it's not refreshing. So now what I'm going to
  1351. 1:39:21do is previously we're just testing the design  and then iterating on that. Um now I'm going to
  1352. 1:39:24discuss like functionality. Hey, this looks great.  I created a new task using the new task button,
  1353. 1:39:30but when I went back to check the list of tasks,  I didn't have a content order in the database.
  1354. 1:39:34So I'd like you to double check why that is. It  may be an issue with the adding to the database
  1355. 1:39:39or it may be an issue with the pulling from the  database. If there's a table problem or something
  1356. 1:39:42like that, let me know. While I was doing that,  I noticed that there was an order options section
  1357. 1:39:47on the right hand side of um the new orders page.  It looks like uh there aren't buttons or anything
  1358. 1:39:52here. Like I can't really toggle this on or  off. So just refactor that so there's toggles
  1359. 1:39:57um and those toggles actually do something and  they're meaningful. And then also make sure that
  1360. 1:40:02whatever we're seeing in this chart, it accurately  reflects the data in the database. And then I also
  1361. 1:40:09noticed when I tried oh on the landing page here  it's a mixture of orange and purple designs. I
  1362. 1:40:15just want you to make everything here purple. The  signin button is um almost transparent. It's very
  1363. 1:40:21difficult to see. And I'm noticing that there's no  way to log out once you're logged in. So just add
  1364. 1:40:25that functionality as well. I need to be able  to log out. Can't just stay logged in forever.
  1365. 1:40:30Cool. So I'm just going to pump all that stuff  in and then I'm going to go. So we're getting
  1366. 1:40:35closer and closer to the end result. Cool. also  just made some additional changes. I'm just going
  1367. 1:40:39to head over to new task. I'll say five ways to  increase XYZ. See in the right hand side we now
  1368. 1:40:44have some toggles which looks nice. And I'm just  going to add some keywords. I like the idea that
  1369. 1:40:49we could pick those. So I'll click save. And I'm  still not seeing it in the database, which is kind
  1370. 1:40:54of annoying. Uh must be some problem. Okay. And  I'm just retesting this now. Create new content
  1371. 1:40:59order. Blah blah blah. I'm click save. And looks  like we actually got it in. There is still some
  1372. 1:41:04fake assignees, I think. So, I'm going to  I'm going to have that fix that. However,
  1373. 1:41:08if I click on this now, you can see that we have  the brief and then we also have some keywords,
  1374. 1:41:12which looks really nice. And then we have  some really nice formatted stuff on the right,
  1375. 1:41:14like details, format, word count, deadline, and  so on and so forth. So, big fan of that. We see
  1376. 1:41:19the ID of the order up ahead, which I guess could  be useful if I'm trying to contact my agency. Hey,
  1377. 1:41:23I can't see a thing on my dashboard. Yeah, what's  the ID? Then, when we go to dashboard, we can now
  1378. 1:41:28see this has been updated. And it looks like it's  using some sort of mathematical formula here to
  1379. 1:41:33divide this so that the top of this is always  going to be equivalent to the total number of
  1380. 1:41:38maximum orders in a in a certain period. So that's  pretty neat. I like that. What else did we need?
  1381. 1:41:43Uh we didn't have the ability to sign out. So I'm  just going to double check. Do I have the ability
  1382. 1:41:47to sign? Oh yes, I do. It's just hiding behind  my head again. So at the very bottom lefth hand
  1383. 1:41:51corner, I click log out. Okay. Now I'm back to the  client dashboard, which is nice. Uh what I'm going
  1384. 1:41:56to do is I'll go back to sign up. Okay. And then  that looks pretty cool. And then I'm just going to
  1385. 1:42:00try go back to the actual landing page. Nice. So  it actually did fix this up. Although this landing
  1386. 1:42:04page needs a lot of work, which we're going  to fix up in a moment. Uh and then cool. Yeah,
  1387. 1:42:09we have the ability to sign up. We have the  ability to sign in. I mean, this is pretty
  1388. 1:42:11solid to me. I don't really think much else needs  to occur. I'm going to modify the design on both
  1389. 1:42:17the signin pages, sign up pages, and the landing  pages. I'm going to make the landing page really
  1390. 1:42:21sexy uh just to wow you. And then yeah, I  think I think that's more or less it. Oh,
  1391. 1:42:26I guess what we should finally do is we should  check to see if we if we have middleware. So,
  1392. 1:42:30what happens when I go slash orders? Notice how  it immediately jumps back to the login page. How
  1393. 1:42:35about if I go /dashboard? Nice. How about if I go  orders new? How about if I go settings? How about
  1394. 1:42:41if I go what else did we have? Notifications. We  got notifications. Nice. So, it looks like our off
  1395. 1:42:47middleware is pretty good right now. Um although  I'm obviously going to have to double check that
  1396. 1:42:50with that big prompt that I talked about earlier.  Now, why don't we modify the design? And once the
  1397. 1:42:54design's ready, we can actually push this and make  this public. And then once this is finally pushed
  1398. 1:42:58and made public, we can um round out the the  end of our site and it'll be really high-end and
  1399. 1:43:02really clean. So again, for design, I'm going to  go to dribble and then I'm going to find a really
  1400. 1:43:07nice high quality uh let's just see if we can  find some really nice high quality screenshots.
  1401. 1:43:12I just want like a super sexy hero header, you  know? I want it to just be insane. So why don't
  1402. 1:43:16we go landing page? I just want this to be the the  best thing ever. This is really neat. Elevate your
  1403. 1:43:24trading experience. Liquid brokers. H I think I'm  probably going to want a white mode thing though,
  1404. 1:43:30like a light mode as opposed to a dark mode. Cuz  if I go dark mode, it'll just seem kind of weird.
  1405. 1:43:37So, I think what I'll do is this section over  here that says AI powered adwords that find lead.
  1406. 1:43:43I think I'm going to roll with this. And then I'm  going to try and have some cool animated section
  1407. 1:43:47over there on the right. So, unfortunately,  I think this is about as big as it gets. Um,
  1408. 1:43:52sometimes, again, they don't want you to uh like  I don't know if you can tell, it's kind of blurry
  1409. 1:43:57here. Sometimes, as I mentioned, they don't want  you to uh copy these designs a ton. I'm still
  1410. 1:44:01going to give it my best effort, though. So, I'll  go back here. I'll paste this in. Excellent. Um,
  1411. 1:44:07what I want to do next is modify the landing  page, the sign-in page, and then the sign up
  1412. 1:44:13page. I'm going to attach some screenshots of the  design. In addition, I'm also going to provide
  1413. 1:44:18you a an animation that you could use to run in  that right-hand side pane. What I'd like you to
  1414. 1:44:24do is I'd like you to combine our design with  the design in the screenshot. I want it really
  1415. 1:44:29clean on the left hand side. I want my main value  proposition. I want some hypothetical logos um in
  1416. 1:44:36the center. You could just use some some plain  text for that. You don't need images. Um, I want
  1417. 1:44:41a relatively long landing page here with sections  for product, sections for pricing, hypothetically,
  1418. 1:44:48uh, and then obviously a button up at the top that  says sign in. And then for the video, I want you
  1419. 1:44:54to use this URL. Now, what I'm going to do is I'm  going to paste this in. And then I'm going to go
  1420. 1:44:59back here. And what I want is I basically want a  cool asset. And then I want to like rotate it with
  1421. 1:45:04AI. And I'll show you what I mean here. Uh, but  basically I just want some sort of asset. Let me
  1422. 1:45:08see what can we get from dribble that looks really  clean. Okay, so for that I'm going to go over to
  1423. 1:45:12dribble and go 3D shape. Um, I really like one  of these shapes, but I think I want this on like
  1424. 1:45:20a white background. Let me see if we could get  something that might make more sense. H organic
  1425. 1:45:263D shapes over here. This is cool. Round egg 3D  shapes. That's kind of neat. Feel like this would
  1426. 1:45:32be nice if we could get a white background on it.  So, why don't we give this a try? What I'm going
  1427. 1:45:37to do is I'm going to take an image of this. Then  I'll go over to Google video. Actually, sorry. Why
  1428. 1:45:45don't we start with Nano Banana? So, I'll go to  AI Studio.google.com. You can sign up for this
  1429. 1:45:52um you know, it's the same account that you  would use for whatever credits you utilized for
  1430. 1:45:57um Gemini and anti-gravity. Then I'll say, let's  see, playground. And I want to generate images.
  1431. 1:46:03I'm going to paste this in. So, I create me a  new organic shape that looks like this except
  1432. 1:46:10with a fully white background. It should look  very sexy and have a purple blue hue to it. And
  1433. 1:46:20then the aspect ratio, I think, is going to be 34,  which is three wide and then four high. And we're
  1434. 1:46:25going to go 2K for the resolution and press enter.  Okay, just ran out of token, so I had to go to a
  1435. 1:46:31different account here. But it's important that  the aspect ratio is 34 and the resolution is 2K
  1436. 1:46:35because that's approximately the same height of  the design that I wanted to copy a moment ago,
  1437. 1:46:39right? Like this one is clearly taller than it is  wide. And I think that's going to be important.
  1438. 1:46:43Okay, so we have this organic looking image,  which is kind of cool. What I'm going to do is
  1439. 1:46:46I'm going to save this image as. So now this is  like our own image. Then I'll head over to VO3,
  1440. 1:46:50which is a state-of-the-art um image to video  generation model. And then what I'm going to do
  1441. 1:46:56is I'm just going to do the same thing. So let  me just switch the accounts here. And then I'll
  1442. 1:47:00link the API key. Cool. And then what I'm going  to do is enable Google Drive access as well.
  1443. 1:47:08And then I'm going to paste in this  image, one that I just generated a
  1444. 1:47:11moment ago. We'll go 9 by6. Just copy this  image. And then go back here. Paste this
  1445. 1:47:18in which I just downloaded. Okay. And  then I'll say uh rotate this slowly. I
  1446. 1:47:26think 6 seconds is probably fine. So that  the last frame is like the first frame.
  1447. 1:47:34Perfect. Uh 100% white background. Okay. I'm going  to press enter. And now V3.1 is generating me
  1448. 1:47:42uh video. Just playing this. Now we have this cool  organic undulating rotating shape which is really
  1449. 1:47:47neat. So I like that a lot. I'm going to download  this. And now I have the video. I'm going to grab
  1450. 1:47:52this. And then I'm just going to dump this into  public. And then I'll say hero header video.mpp4.
  1451. 1:47:57Okay. And then um I initially said URL, but I  guess what I really meant was like inside of my
  1452. 1:48:04folder. public/hero header video.mpp4. Also put a  dot here. Uh cool. I'm just going to press enter.
  1453. 1:48:15And then I'm going to give it some time and let  it go on its way. Okay. Landing page design is
  1454. 1:48:19looking all right so far. I'm not a big fan of  this video now that I'm looking at it. Like I I
  1455. 1:48:23would love it if it just blended in seamlessly,  but for whatever reason, the background is not
  1456. 1:48:27white. We could remove the background and then  we could remove that border and I think it would
  1457. 1:48:30look a lot sexier. I'm partial. I mean, I might  play around with it a bit. Um, we got the logos
  1458. 1:48:36down here. Sign in button top rightand corner.  That's nice. I think we just need to align uh
  1459. 1:48:41what's on like the the left hand side and stuff.  So, yeah, I'm going to do that in a second. Sorry,
  1460. 1:48:45I just realized I was dictating. And then I'm  just going to give it some instructions. Hey,
  1461. 1:48:49this looks solid. Why don't we align all content  to the hero header? Because right now some of the
  1462. 1:48:56sections are really tight. So push it out so that  everything's at the same width as the hero header.
  1463. 1:49:05Um I'm loving the colors. Something with the graph  under the why they prefer Taskbo section looks a
  1464. 1:49:12little bit weird. I think the numbers on the cards  of the maximize your traffic with the content
  1465. 1:49:19engine that generates section um are broken or  something because they're being cut off. So fix
  1466. 1:49:25those. And then everything else looks really  solid. Just update the business name from taskb
  1467. 1:49:31to content hamster as well. Uh and just do that  across the entire app. And then while I'm at it,
  1468. 1:49:39I'm going to see if I could find something that  looks a little bit better for that section here.
  1469. 1:49:43Okay, I found this video and I really like  this. I also think probably because this
  1470. 1:49:47is already optimized, like the file size isn't  really big, I'm probably just going to use it.
  1471. 1:49:51This is not a live SAS app. So, Ashkat Ash Moana,  great job on said design. Um, we're just going to
  1472. 1:49:56be using this as a a demonstration purpose. Um,  it looks like he also allows you to explore or
  1473. 1:50:02tweak this scene by checking it out in his spline  community page. I don't even know what that means,
  1474. 1:50:07but I think it's like a way you can share designs  and stuff like that. So, that's kind of neat. Oh,
  1475. 1:50:11wow. I can actually revolve it. That's so cool,  dude. Wow. So, I guess you could probably run
  1476. 1:50:15this as 3D in your browser. Anyway, we don't want  to do that. That's just a little too much. Um,
  1477. 1:50:19but I'm going to instruct the agent to use that  image and then make sure the orb doesn't get
  1478. 1:50:24cut off weirdly. Also had a couple of sleek  cards placed on top of the video with a glass
  1479. 1:50:27isomorphism effect. So, something to break it  up a bit. And then I'm just going to jump back
  1480. 1:50:31over to our app here so we can see um as it's  actually being developed in real time. You can
  1481. 1:50:36see we changed the name to content hamster.  Kind of silly, but uh whatever. This has now
  1482. 1:50:41done everything perfectly with left-hand side  um margin match up which is nice. Why they
  1483. 1:50:46prefer content hamster? This has now been spread  out. So the graph is no longer all weird. Again,
  1484. 1:50:50perfectly margin aligned. Something with the  numbers is still off. So I'm going to have it fix
  1485. 1:50:54that as well. Let's just do that before I forget.  Hey, numbers on cards are still a bit weird.
  1486. 1:51:04Screenshot for reference. Then as I scroll  through, is there anything else? plus premium.
  1487. 1:51:10Okay, ready to level up your process. Cool. And  then we also have a bunch of buttons down at the
  1488. 1:51:16bottom here that obviously don't really work.  Okay, cool. This looks really clean. I'm liking
  1489. 1:51:19this. I'm liking this a lot. Um, I'd say the only  thing that's missing is probably like the coloring
  1490. 1:51:24across the board. Um, what I'm going to do now is  I'm just going to match all of the colors to this
  1491. 1:51:30because I just love the way that that looks. Uh,  I'm just going to take a screenshot here and then
  1492. 1:51:35I'll say colorfinder online and I'm just going to  paste in this color. And as we see here, there's
  1493. 1:51:45this hex code. So, I like that a lot. And what I'm  going to do is I'm just going to paste this in as
  1494. 1:51:48well. Also, I want you to update the primary color  scheme across the entire application so that it is
  1495. 1:51:55that shade of baby aqua blue. Looks really cool.  use slightly darker shades of blue as accents,
  1496. 1:52:02etc. And then for the accents, I guess I'll  just go back to this. Screenshot it. Paste
  1497. 1:52:11this in here. And then we can use stuff like this  as well. Um, and let's go a little lighter here.
  1498. 1:52:21We'll go this dark. Darkest. Cool. And now it's  going to go through the entire app and just change
  1499. 1:52:26it to reflect like the background colors of this  which I think are going to be really cool. Um,
  1500. 1:52:31obviously I don't want, you know, us not to be  able to see the text. So I am just going to be
  1501. 1:52:34around like, you know, if this is that color, it  will seem kind of weird. Right now we obviously
  1502. 1:52:38have a cool purple thing going on with all the  highlighted text being purple and then these
  1503. 1:52:41things being purple. I do think it would just  match really really nicely and seamlessly if we
  1504. 1:52:45had that. So we'll give that a try. All right,  this is looking way better. I'm loving how the
  1505. 1:52:48baby blues actually reflect what's going on here.  Let's click try out for free. Um, actually I guess
  1506. 1:52:53I already have an account, so I'll just log in.  But we are going to test that out in a second.
  1507. 1:52:57Looks like those numbers have been fixed, which  is cool. We got that slight zoom in on each card
  1508. 1:53:01as well, which I really like. And then baby  blue effect everywhere. That's gorgeous. Um,
  1509. 1:53:05this little content output graph is still purple.  So I'm just going to see if we change that. One
  1510. 1:53:09thing I didn't really talk about was mobile  optimization, but um, Gemini Mobile optimizes
  1511. 1:53:13everything really, really well just out of the  box. Obviously, we do have some minor issues
  1512. 1:53:16with the bounding boxes of this um, like video,  the border. Uh, but this is something that would
  1513. 1:53:21probably be better done by actually replacing the  core underlying asset because the resizing of the
  1514. 1:53:25border box occurs basically perfectly. Um, but  just giving you an example of what it might look
  1515. 1:53:30like on a tablet. As you can see, everything  is still basically perfect. I haven't ran into
  1516. 1:53:34major issues so far. Even the numbers and stuff  like that are visible. And if we scroll all the
  1517. 1:53:37way down, the biggest problem is just there's this  little black overlap. I want you guys to know that
  1518. 1:53:41I haven't even done mobile optimization yet, which  is typically just like a line in the prompt. Um,
  1519. 1:53:45really, really wild that it does this good of a  job without me even having to tell it. Cool. And
  1520. 1:53:49now we have everything changed. So content output  is nice and changed. Uh you know the the the look
  1521. 1:53:54of the little bubbles here goes up. I mean this is  basically exactly what we wanted. I also changed
  1522. 1:53:58the name to content wheel obviously. So why don't  we now sign up and go Nick Sarif. We'll call
  1523. 1:54:04myself Leftclick Inc. We'll just use a slightly  different email this time just so we could retest
  1524. 1:54:08the sign up. Uh let me just make sure this is a  simple ass password. That'll always be the same.
  1525. 1:54:13Cool. We're going to click sign up now. Account  created successfully. Please check your email to
  1526. 1:54:17confirm your account. Uh, I'm now going to sign  into the specific mailbox that gave me that. So,
  1527. 1:54:22let's go here. You can see it's saying to confirm  my sign up here. So, I'm just going to go back and
  1528. 1:54:26then I'll now be able to sign in with the specific  email that I just put in. We'll click sign in.
  1529. 1:54:32Just delete all this stuff. Cool. And I'm just  going to zoom in a bit so we can see. Obviously,
  1530. 1:54:35I have a really big desktop so it won't always  look like that. Um, cool. We have total tasks.
  1531. 1:54:40You can see the styles been updated a little blue  here because I just wanted it to be blue. Um,
  1532. 1:54:44task completion is still purple. So, I think I  may update the graph. I don't really know to be
  1533. 1:54:48honest. It might be okay. My tasks inbox. Cool.  All that stuff looks good. So, we'll now test
  1534. 1:54:53the new task. I'll say, "Hey, this is an example.  Here's my example brief ABC." And then over here,
  1535. 1:55:02we'll go 13. I'll click save order. Cool. We now  have it in our database. It's now a draft. So,
  1536. 1:55:08content is being written. Your writer's currently  working on it. You'll see it when it's ready.
  1537. 1:55:11Inbox. Cool. Um, awesome. I mean, this looks  pretty solid to me. I don't see any major
  1538. 1:55:15issues. So, we'll go to settings. We can update  things. I don't know if this got saved, that
  1539. 1:55:20little leftclick thing. Yeah, it doesn't look like  that did. So, now that we basically have like the
  1540. 1:55:25whole app ready to go, we just need to make a few,  you know, minor changes before we deploy. Hey,
  1541. 1:55:31uh it doesn't look like the company. Okay. And  then after a full endto-end check, this website
  1542. 1:55:36and app is now ready to be pushed um and actually  deployed. That deployment is going to occur on
  1543. 1:55:41Netlifi like I talked about earlier. And I'm going  to give you guys a simple simple process that you
  1544. 1:55:45guys could use in order to actually push that out.  For now, I'm going to go grab some lunch since I'm
  1545. 1:55:48pretty hungry, but I'll BRB. So, the strategy  I'm going to use in order to push this site and
  1546. 1:55:52make this web accessible just like we did with our  old website is to use Netlefi. And in order to do
  1547. 1:55:59that, we're going to use Netlefi CLI and then give  the vast majority of the work to the model. Um,
  1548. 1:56:06so Netlefi CLI is basically just a command line  interface. That's what the CLI stands for. That
  1549. 1:56:12lets previously people like you and I, but now  mostly agents interact with the Netlefi API,
  1550. 1:56:17which is like their little application programming  interface. The way that you uh do various actions
  1551. 1:56:23on Netlfi using HTTP requests autonomously for  you. They can actually do most of it. So what I've
  1552. 1:56:29done here is I've actually just said, hey, I want  you to build this and then I want you to push it
  1553. 1:56:33on Netlfi. We've gone through the whole build.  We've gone through phase one, two, superbase,
  1554. 1:56:38you know, phase three and now what we're doing  is we're doing this final production deployment
  1555. 1:56:42and this is uh you know just uh part and parcel  more or less the final step of getting this thing
  1556. 1:56:49on the internet. Now, I should say that when you  actually push things to production, that's what
  1557. 1:56:54that's called, typically there are some issues  because the development environment that you run
  1558. 1:56:59on your local computer is always going to be a  little bit different than whatever the heck the
  1559. 1:57:02server is using. And so, sometimes you have  to make minor changes to the site. Sometimes
  1560. 1:57:06you have things that work on your device, but then  don't work obviously on the production server. So,
  1561. 1:57:11you have to, I don't know, modify like the the  way the database works, some of the permissions
  1562. 1:57:15and stuff. And that's just part of dealing  with any sort of full stack application.
  1563. 1:57:19wasn't a big deal with our website because our  website was obviously not super interactive. It
  1564. 1:57:23was just a bunch of uh links. But this has some  back and forth and that's what's important. So,
  1565. 1:57:27as we scroll up here, we can see this has actually  gone through the build process, which is basically
  1566. 1:57:33taking our website or what our website should  look like and then turning it into like an
  1567. 1:57:37actual instantiated version of the site. That's  what that is. Um, and now it's going through the
  1568. 1:57:41installation process for the actual Netlifi CLI,  which is a little package. And now it's going to
  1569. 1:57:45communicate with the Netlefi CLI. And all we  have to do is we just have to authenticate. So
  1570. 1:57:50assuming we have an account set up and stuff  like that. And what we have to do is we have
  1571. 1:57:52to go and actually log in. So what I'm going to  do is I'm going to open this up. So I'm going to
  1572. 1:58:00um give it a new terminal tab which is what it's  asking for. You can do that by going control shift
  1573. 1:58:06um tilda I think it's called. It's like that  little thing in like the top leftand corner.
  1574. 1:58:11It looks kind of like this. Uh you should also be  able to do this by going up to the top and then
  1575. 1:58:16going terminal and then going new terminal. And  then I'm just going to paste this Netlefi login
  1576. 1:58:21command. And in my case, you know, I've already  done this on my machine a bunch of times. So it'll
  1577. 1:58:25say it's already logged in. In your case, uh you  know, if you haven't done this login before, it'll
  1578. 1:58:29just pop up a little Netlify panel and then you  can do it there. So I'm going to say done. And now
  1579. 1:58:33it's going through the various building procedures  and so on and so forth. So, my expectation is I
  1580. 1:58:38mean there's like a 50% chance we oneshot this  because we are using a pretty standardized
  1581. 1:58:41framework called next.js. Uh there's a 50% chance  that we're going to have to go back and forth.
  1582. 1:58:46It's saying the deploy is live. I'm just going  to refresh this and check for myself. Okay. And
  1583. 1:58:50you can see we did push the actual website side  of things up. So, that looks good. Just exit out
  1584. 1:58:55of this so we can get like the the full glory of  the site. And I'm not seeing any major problems
  1585. 1:59:00here versus the one that was on my machine, which  is cool. You know, we got these little buttons.
  1586. 1:59:06premium get started now. Okay. And I mean, we  haven't added links to all these yet, which is
  1587. 1:59:09why these aren't actually popping up. Uh like  changing my um little cursor when I mouse over,
  1588. 1:59:14but that's okay. And now what I'm going to try  is actually the interactive component. Cool. So,
  1589. 1:59:18we have the account created successfully modal.  And that's great. I'm now going to head over to
  1590. 1:59:23that specific email address and just check if we  have the email confirmation message. Okay, we have
  1591. 1:59:27this right here. So, I can confirm my mail. And  now we're starting to see one of the issues. So,
  1592. 1:59:32error parsing package.json JSON file. And it looks  like the reason why we're getting that is notice
  1593. 1:59:37the URL up here. The URL is not actually uh the  publicly accessible URL. It's this localhost 3000.
  1594. 1:59:44And so the way that you know user signups usually  work is basically there'll be some URL here slash
  1595. 1:59:50some code and then the agent will configure your  Nex.js or whatever full stack app framework you're
  1596. 1:59:56running to like accept this code and then  use that to verify the account. But basically
  1597. 2:00:00what's happened here is the default sends us to  localhost 3000. And so I know what the issue is,
  1598. 2:00:05but just for the purposes of like debugging and  stuff like that, I'm actually going to just take
  1599. 2:00:08this to my agent and I'll see what the agent says.  We have to go back into our Superbase settings
  1600. 2:00:12and then alter it. But I do just want you guys to  know like how this works if you guys are actually
  1601. 2:00:16debugging it. So I'll say I received this error,  this um call back when setting up my account.
  1602. 2:00:27this isn't the right URL. What should I do? And  you'll see here it'll instruct us to go to our
  1603. 2:00:34Superbase and and make some minor changes. And  then it's going to tell us to update our Superbase
  1604. 2:00:38dashboard settings. So, go back into my dashboard,  which is right over here. And then there's going
  1605. 2:00:44to be an authentication page right over here on  the top left. And then it's either going to be
  1606. 2:00:49an email or somewhere else. Like we can actually  turn off the um confirmation completely. This is
  1607. 2:00:54the email that Superbase sends them. That's why  it looks a specific way. And I don't know, to me,
  1608. 2:00:58it kind of looks a little ugly. So, obviously, if  I were running a full production app and I were
  1609. 2:01:02making all those uh little bells and whistles, I'd  make this look really pretty. But I think there's
  1610. 2:01:07actually a way to change the URL. Okay, here  it is. It's right under URL configuration. It's
  1611. 2:01:12a site URL. And so, what I'm going to do instead  is I basically just want to get the the live URL,
  1612. 2:01:18which is this one here. Just going to paste that  in. Okay. And I'm going to remove that back slash.
  1613. 2:01:24So now this is going to be the URL that it uh  basically redirects us to on Superbase's side
  1614. 2:01:29cuz Superbase handles the the signups and stuff  like that. And now when I go back to the app,
  1615. 2:01:35I don't even have to actually make any uh major  changes like I don't have to rebuild the app or
  1616. 2:01:39anything. Then I can give it an email. I click  sign up here. And now we have another email sent
  1617. 2:01:48to another one of my addresses. There you go. It's  right here. When I mouse over this, you guys can't
  1618. 2:01:52really see in the bottom lefthand corner, but  I'm no longer going to localhost. And you can
  1619. 2:01:57see if I click on this, takes me to contentorb  dashboard.netifi.app/lo. So here I can actually
  1620. 2:02:06um now jump in and log into the app. Cool. So  that's one of the first changes I would say if
  1621. 2:02:13you're building something on production versus  doing something locally. We just have to change
  1622. 2:02:16the URL that the authentication goes to. So  we just did that. Now it's nice and clean.
  1623. 2:02:20And I'm scrolling up and down here, making sure  there are no major issues that are egregious. I'm
  1624. 2:02:26not seeing any problems. I guess the company isn't  filling in. So, we can change that. Well, I write
  1625. 2:02:31this. Save. Give this a refresh. Yeah, looks like  the company in the profile details isn't filling
  1626. 2:02:35in. So, I'm just going to take a screenshot  of this and then I'll paste this in. And then
  1627. 2:02:39while I'm like before I actually send this, cuz I  prefer just to do a bunch of stuff, not just one,
  1628. 2:02:43let me test the new order. This is a new order.  What's up? And then over here, I'm going to go
  1629. 2:02:54one word and then I'll save. Okay. So, yeah, this  is actually in my database now, which is pretty
  1630. 2:02:58cool. I can click on this. Looks like the rest of  this stuff is is here, which is nice. Anything in
  1631. 2:03:04my inbox? Nope. That's cool. And then my actual  orders do populate, which is nice. And we don't
  1632. 2:03:11actually have like the ability to like we don't  have any people on our team, but obviously we
  1633. 2:03:14could have added some, which is why we still  have those little um little fake Notion-esque
  1634. 2:03:18people there. I wonder where they're getting those  images from. That's kind of cool. Okay, so uh we
  1635. 2:03:23have dashboard. Did we I think we checked settings  as well. Yep, that looks pretty good. And I think
  1636. 2:03:29every other toggle here probably works. Let me  just try searching the tasks. So I'll just go O
  1637. 2:03:38H. Okay, so yeah, clearly it's just searching  based off the letters. If I type in new order,
  1638. 2:03:43if I type in old order, then it won't be.  Okay, cool. So if we had 20 in here, you know,
  1639. 2:03:46that might actually be useful. And let me just  check the sign-in page. Okay, cool. So, we're
  1640. 2:03:51immediately being logged in when we click the  signup page. And then, you guys can't see this,
  1641. 2:03:54but in the bottom left corner, I'm just going  to click log out and see what happens. Okay,
  1642. 2:03:57so when you click log out, it takes you straight  back to the login page, which is the desired
  1643. 2:04:00expected behavior. And then nothing is prefilled.  Let's now check all of our routes. So, I would
  1644. 2:04:06always recommend going through every single one.  So, that's dashboard. This is settings. This
  1645. 2:04:10is orders. This is orders. um I think and then  slash new and then there's also a notifications.
  1646. 2:04:17So notice how none of these are automatically  signing in which means some of our off uh is
  1647. 2:04:21fine and you know all of our animations and stuff  like that look really clean and uh there there are
  1648. 2:04:26no problems on that end. Okay. And then I'm just  going to do a final spot check because although I
  1649. 2:04:31told it to um you know mobile optimize the site, I  do want to make sure that it is mobile optimized.
  1650. 2:04:36This looks really clean. You know the only issue  here is with this little background not being
  1651. 2:04:41necessarily the same as that. I guess we could  just change the background color of this whole
  1652. 2:04:44element. That might actually help. So, yeah, why  don't I do that? That's a really cool thing. Um,
  1653. 2:04:48why don't we adjust the background element of our  little orb to this? Adjust the background color of
  1654. 2:04:58the element that contains the animated orb to be  the same as that background color of the orb. This
  1655. 2:05:02should be our light aqua baby blue. Okay, that  looks nice. And then just scrolling through here.
  1656. 2:05:08Any other issues with the mobile optimization?  Just make this really nice and small. Be 100%
  1657. 2:05:14sure. Nope. Everything here looks like Oh, you  know, there is one. Looks like this learn more is
  1658. 2:05:20not immediately underneath the get started now.  So, that's one final thing that I'll do. I'll
  1659. 2:05:26finally say also the learn more button is not um  underneath the what was the name of that button?
  1660. 2:05:33Get started now button. So, I'd like you to line  them up on mobile. Now I should know because
  1661. 2:05:37this is no longer local on our computer. It's on  netlefi the uh debug in an iteration loop takes a
  1662. 2:05:44little bit longer. Naturally when we were just on  our computer anytime we'd have an issue we would
  1663. 2:05:48just say hey rebuild it. It would rebuild it and  then we'd immediately have access to it. Right?
  1664. 2:05:51But here we actually need to make the changes  locally on our computer push them to Netlefi
  1665. 2:05:55have Netlefi do the build and because Netlefi is  sort of doing free server space takes longer and
  1666. 2:06:00then we actually have to go online and then um  you know take a peek at the website. But anyway,
  1667. 2:06:04I'm uh just going to open this up now. This is the  production version. I should be able to see the
  1668. 2:06:10background and everything like that. Nice. And now  we have more or less my exact desired behavior,
  1669. 2:06:15which is how that orb just looks like it's  floating. And it doesn't matter how big or
  1670. 2:06:19small the website is. It's just like perfectly  contained within those bounding boxes. Super
  1671. 2:06:24clean. Um and then I just had a couple of those  other changes. Just going to verify that those
  1672. 2:06:28are good. The last thing I'm going to do is I'm  just going to go down to my security audit prompt.
  1673. 2:06:32scroll all the way down to the bottom. And  there's just a little bit of nuance here. Um, I'm
  1674. 2:06:36not actually going to do this in the same thread  that I launched and built the entire website. So,
  1675. 2:06:40I'm going to use Claude Code for this instead of  Gemini. And the reason why I'm doing it is cuz I
  1676. 2:06:44don't want any context. I basically want the model  to look at this entire codebase as if it's new,
  1677. 2:06:48fresh, and not mine, like somebody else's. And I  want it to like run through this whole checklist
  1678. 2:06:52and to end and tell me whether or not it's  configured. Okay, so I just copied this all.
  1679. 2:06:57I'm going to head back to anti-gravity. Close  these tabs. And I should just be able to do so
  1680. 2:07:01by clicking close all. Let's make this smaller  because we're going to have clawed code instead.
  1681. 2:07:07And then what I'm going to do is I'm going to  paste this in. Then I'm going to say don't make
  1682. 2:07:12any changes. I just want the audit. Okay. And I'm  going to pump this in. And now cloud code is going
  1683. 2:07:19to go pass one discovery map the full architecture  and then more or less tell me, you know,
  1684. 2:07:24what's good, what's bad. And I'm doing this for a  couple of reasons. Um, obviously I want no context
  1685. 2:07:29as mentioned, but I also think that Claude is a  lot more interpretable than Gemini right now. If
  1686. 2:07:33you guys check out the thinking tabs here, and  if you compare them with the thinking tabs of,
  1687. 2:07:38you know, Gemini, Gemini uses language that just  doesn't really make much sense. Um, you know,
  1688. 2:07:42when you look at it, it's not as interpretable.  I'm now taking action to apply the color
  1689. 2:07:45adjustments as previously decided, focusing on  the background's visual look. I'm now proceeding
  1690. 2:07:48by updating the styling to use desired hex code.  You if you look at it and just compare it to this,
  1691. 2:07:53this is a lot more interpretable. I now have a  comprehensive understanding of the codebase. Let
  1692. 2:07:56me compile the architecture summary and then  work through every checklist item. They give
  1693. 2:07:59it to me sort of in plain English. And so the  interpretability is pretty important when you're
  1694. 2:08:03talking security, right? Um in addition, you  know, I just think Claude is a little bit better
  1695. 2:08:07at like security based stuff right now. Okay,  so I'm I'm reading through everything here. It
  1696. 2:08:12looks like most of our audits are correct. We  do do console. Calls, which is important. Um,
  1697. 2:08:18this is basically a way to minimize the attack  surface uh and then minimize or maximize
  1698. 2:08:23operational security. We're not really giving  away how our underlying tool works. So that'll fix
  1699. 2:08:28that. Startup validation. Okay, so we need some  sort of startup validation here. It looks like
  1700. 2:08:36we can't tell whether or not the RLS is enabled  um because we don't actually include the files in
  1701. 2:08:40the codebase, but that's okay. We are actually  good on RLS. Uh that's why it's giving us this
  1702. 2:08:44warning message as opposed to a no. We're good on  SQL injection, security definer functions, same
  1703. 2:08:49thing as uh previously. So we could have um claude  like connect to our superbase instance via API if
  1704. 2:08:55we want. And I'm just going to take all of this  default deny routing fails. This is important.
  1705. 2:09:02Remember how I talked about O middleware? This  basically just immediately denies all requests
  1706. 2:09:05that don't have some form of authentication. Right  now our app doesn't do that. And you know, at the
  1707. 2:09:11end of the day, we while are okay on most things,  we're still missing some uh some things there. So,
  1708. 2:09:17I'll say excellent execute all of the changes.  Okay. So, I'll say um the SQL stuff was already
  1709. 2:09:27taken care of. RLSTC, but thanks for pointing  that out. Execute all of the remaining changes
  1710. 2:09:35and change SQL checklist items to green. And now  it's going to go through and then work through the
  1711. 2:09:42fix the systematically form. And just to give you  guys some more visibility in the security side of
  1712. 2:09:45things, you know, previously we had a line in our  code that said if there's an error, we actually
  1713. 2:09:49add all of the superbase insert error details  here. This is actually just like gives a bunch
  1714. 2:09:53of information about the way that our superbase  database is configured. And that's just because
  1715. 2:09:56Jeem and I wanted to write it in the way that was,  you know, debugable for us if you guys remember.
  1716. 2:10:00Well, this now went through it identified that  and it changed that to fill to create order,
  1717. 2:10:04which is just much more general. And um that both  gives us the ability to quickly see if there is an
  1718. 2:10:08issue, but then it doesn't expose any of our  underlying in infrastructure architecture if
  1719. 2:10:14somebody actually wanted to attack us. As you  can see, we have most of the changes that we
  1720. 2:10:16talked about before. We have allow list routing.  We have client side user ID filtering. Okay,
  1721. 2:10:20server side validation. We added what's called  an off call back route. Um we have environment
  1722. 2:10:25variable validation. And we also had some console  leaks that we've since cleaned up. And just
  1723. 2:10:30scrolling through to get to that checklist,  you know, the vast majority of these are now
  1724. 2:10:34green. all the issues that we had previously have  been taken care of. And so 5.1 which was a dev
  1725. 2:10:39dependency and then 6.2 which was some built-in  rate limiting. You know, we don't have control
  1726. 2:10:44over that. And these aren't really large security  issues as well, which is why they're in this
  1727. 2:10:48yellow little warning label instead of the X. Um,  you know, we're now good. We've basically solved
  1728. 2:10:52for the 8020. The vast majority of lowhanging  security fruit do no longer apply to our app.
  1729. 2:10:58And while I probably wouldn't scale this to like a  million users without at least having some sort of
  1730. 2:11:02security person look this over, it's pretty dang  good. I just did a final walkthrough of the site.
  1731. 2:11:06We have the animation, which was previously  hidden because of that middleware update. Um,
  1732. 2:11:10some of our icons are missing as well because  of that same thing, as well as the login uh and
  1733. 2:11:14signup routes, as well as every other feature in  our network. So, this is an example of like that
  1734. 2:11:18extra step at the end that a lot of people don't  want to do because obviously it takes, you know,
  1735. 2:11:22an additional 15 or 20 minutes. It's about how  long it took me, but I highly recommend it if
  1736. 2:11:25you do plan on making your app live. and actually  launching it to more than just yourself and your
  1737. 2:11:30close friends and family. But congratulations,  we have now built an endto-end full stack app
  1738. 2:11:35with login, authentication, signup. We have a  database where we store records and queries and
  1739. 2:11:40then also a pretty sexy landing page. You guys  now know everything that you need in order to
  1740. 2:11:44basically take this knowledge and then go out and  actually just vibe code an app. What I want to do
  1741. 2:11:47next though is I don't just want to vive code any  app. I want to take you guys to a higher level of
  1742. 2:11:52understanding of modern software engineering  principles cuz I think it's one thing to be
  1743. 2:11:55able to just use natural language to, you know,  communicate with agents and have it do something.
  1744. 2:11:59But some of these architectural decisions that  the agents are making are actually controllable
  1745. 2:12:02by you. And if you know even 10% more than  the average Vibe coder, you can, you know,
  1746. 2:12:07rather than this process takes 2 or 3 hours, you  can basically just build like your little starter
  1747. 2:12:12kit with um your preferred stack, your preferred  tooling, and then some preferred examples.
  1748. 2:12:17you can get to the point where you could actually  just like oneshot uh an app like this. Maybe not
  1749. 2:12:20completely oneshot but like 1.5 shot it. Take uh  app creation which previously might have taken
  1750. 2:12:25a very very long time because of all these  small little decisions that you and I have
  1751. 2:12:28to make and then get it to a point where it's  it's much faster. And not only that, I think
  1752. 2:12:32you'll probably gain a lot more appreciation for  software engineering as a whole and then become a
  1753. 2:12:36better developer um whether or not you're working  in conjunction with agents. So let's do that next.
  1754. 2:12:41Now, I should know that this isn't going to  be a comprehensive software engineer degree
  1755. 2:12:46or anything. In fact, I know there are going  to be some software engineers in the comments.
  1756. 2:12:50They're going to look at what I'm talking about  and probably laugh. They're going to say, "That's
  1757. 2:12:53not how to actually host. That's not how databases  work or whatever the heck." The reality is, you
  1758. 2:12:59don't need to know all of the internals of how all  of these different things were put together. These
  1759. 2:13:04are essentially things that were built over the  course of the last 50 or 60 years. And nowadays,
  1760. 2:13:09even the most competent developers typically  just stand on the shoulders of giants. And so,
  1761. 2:13:13I'm going to give you a very high level overview  here. And this high level overview will, like the
  1762. 2:13:16rest of the course, be the 8020 that allow you to  dive deep into specific parts if you so want to.
  1763. 2:13:22Um, but you won't necessarily need to hear me  yap on for 700 hours about different database
  1764. 2:13:26architectures. Okay, so we're going to start with  hosting. To make a long story short, hosting is
  1765. 2:13:31just the technical term for running your web  application on a server. works on my machine
  1766. 2:13:37is the scariest thing a developer could say. So,  it's important to do this right. You know how a
  1767. 2:13:42few minutes ago when I was developing that app  and then pushing it live, there were immediately
  1768. 2:13:46some problems. Well, what a lot of developers will  do is they will develop entirely locally and then
  1769. 2:13:51they'll say, "This works fantastic, amazing." And  then they'll leave the pushing and the deployment
  1770. 2:13:55and and you know, all the hosting and stuff like  that is sort of an afterthought. And then when
  1771. 2:13:59they actually do push it, then there's a bajillion  problems and the app doesn't really work. And then
  1772. 2:14:03as you saw there's also a longer feedback loop  because now this is live on the internet it's not
  1773. 2:14:06on your machine and that longer feedback loop can  make you know that last mile problem where you've
  1774. 2:14:10done 99.9% of the work uh of your app but then  that.1% takes like 100 times longer just because
  1775. 2:14:15of the nature of your your prepare preparation  or lack thereof. So in order to really get this
  1776. 2:14:21we just need to give a brief highle walkthrough  of how communication um on networks tends to work
  1777. 2:14:27or like on apps. Basically on the left hand side  here we have a client. And for all intents and
  1778. 2:14:32purposes, let's just say this is um your browser.  Okay. Now client is just such a silly name. I
  1779. 2:14:38would say not a lot of people really understand  this, but I just replace basically all instances
  1780. 2:14:42of the term client with just your browser for  now and everything will make more sense. Now your
  1781. 2:14:46client, okay, it's just your browser. It needs  to communicate with a server in order to have
  1782. 2:14:52some sort of back and forth. And so this server,  okay, could actually be like your um computer if
  1783. 2:15:00you're developing locally or if you know you're  pushing to some, you know, service or whatever,
  1784. 2:15:07it could be something like well maybe Nellifi  isn't the right example, but I don't know. Yeah,
  1785. 2:15:10I don't know if you guys ever used Hostinger for  instance, not affiliated with them, but um that's
  1786. 2:15:14a good example of one. Or let's just see Hostinger  alternatives. Blue Host, if you guys have ever
  1787. 2:15:21developed a WordPress website or Cloudways or Site  Ground or Insta. Basically, these are services out
  1788. 2:15:28there that run computers just in the cloud that  you can then access in order to like push stuff on
  1789. 2:15:34it. Okay? So, what happens is your client, okay,  your browser will communicate with the server,
  1790. 2:15:39which if you're running stuff locally is either  just your computer or it's somebody else's
  1791. 2:15:43computer on hosting or site ground or whatever  other service. And then it'll send initially some
  1792. 2:15:49very simple and brief requests, okay, for things  like um you know site HTML. It'll send uh requests
  1793. 2:15:57for things like uh database data and whatnot.  And so your server has the ability to do a lot
  1794. 2:16:02of its own logic and whatnot. And so in general,  what clients um are for are they're just for like
  1795. 2:16:08presentation. And then what servers are for is  they're more for like the heavy lifting and the
  1796. 2:16:12logic and the validation and stuff like that.  That's why server side validation is much more
  1797. 2:16:15important than client side validation. That's why  it's a big security risk. The thing is in addition
  1798. 2:16:19to the server, there's like a third piece called  your database where we actually store like a
  1799. 2:16:24row or tabular data. And you know, for all intents  and purposes, your database is just one big Google
  1800. 2:16:29sheet. There's like an ID column, there's like a  date created column, there's like a I don't know
  1801. 2:16:34value column, and then there's uh just a bunch of  stuff here. um where basically what your server
  1802. 2:16:41does is it will make a request to this database  to receive specific pieces of data that the user
  1803. 2:16:46has requested. So if the user has an ID of 23 foi  whatever, okay, and then you know the request is,
  1804. 2:16:53hey, I just want you to grab the value. What it'll  do is it'll return 2 3 4 2 3 4 um over and over
  1805. 2:16:57and over and over again. Okay, so that's that's  pretty cool. Um the reason why we split these two
  1806. 2:17:02up is just servers are obviously computers. This  is obviously just data. Data are not computers,
  1807. 2:17:07although computers can contain data. You could  theoretically contain a bunch of information on
  1808. 2:17:10your server, but why would you pay for all that  when you could just use like a highly optimized
  1809. 2:17:14service that just stores a bunch of records and  then communicates really quickly. So anyway, let's
  1810. 2:17:18say our client is requesting some data. Like if  you if you go back to our app, um it's requesting
  1811. 2:17:23that like little dashboard data. Let's see how  many orders do we have in the database. What it'll
  1812. 2:17:28do is, you know, we we'll first we'll sign onto  our app. We'll initially make that request to the
  1813. 2:17:32server. It'll return a bunch of HTML and um any  pre-existing or cache data, okay? And then it'll
  1814. 2:17:36visualize it. And then after, you know, you the  user will navigate on the website and you'll say,
  1815. 2:17:40"Hey, you know, I want to, you know, you'll  you'll click uh the dashboard button and then
  1816. 2:17:44that'll be like, hey, you know, I want to go grab  this data and see how many records I have." So,
  1817. 2:17:47what'll happen is we'll send that request  over to the server. The server has a bunch of
  1818. 2:17:51um pre-built logic basically that says, "Hey,  when a user requests a specific dashboard data,
  1819. 2:17:58I want you to call the database using this format  and then retrieve it." And then we'll say, "Hey,
  1820. 2:18:02you know, we want the dashboard data." It'll  do this in a slightly different language,
  1821. 2:18:07typically SQL, although there are no SQL databases  as well. And then it'll return, you know, that
  1822. 2:18:12dashboard data. The server will do some additional  validation if it needs to, and then it'll just
  1823. 2:18:17return that to the client. And so this is just a  loop that goes on over and over and over and over
  1824. 2:18:20and over again. If the client updates something  like let's say we create an order, well, it's the
  1825. 2:18:24exact same thing. We'll just send a request to the  server. The request will say create order. Server
  1826. 2:18:29will be like, okay, cool. So here's how I create  an order. Then it'll take that request and send
  1827. 2:18:33it to the database which will then add a new order  to like your orders table. So very very high level
  1828. 2:18:38um overview of how basically these modern web  apps work. And I'm going to talk a little bit more
  1829. 2:18:42about like the prevailing frameworks in a second  because there are now apps out there kind of like
  1830. 2:18:46this service I'm using right now called Excaladraw  which does things both online but also locally.
  1831. 2:18:50And you can really dive deep into that rabbit hole  if you want. But um without further ado, what's
  1832. 2:18:56the actual development process look like? Well,  for us it's basically we just start local. So when
  1833. 2:19:00we start local, we run both our client and our  server on the same computer, right? Our client is
  1834. 2:19:04like our browser and then our server is just like,  you know, your your your computer running that
  1835. 2:19:08process. Then we test and verify just like I did  a moment ago for my app. And then once we're done,
  1836. 2:19:14we push to what's called a staging server, okay?  Which is sort of like an intermediary between
  1837. 2:19:19um having everything on your machine and then have  everything accessible to your customers. Once it's
  1838. 2:19:23on a staging server, we then test and verify.  And then once we're done testing and verifying,
  1839. 2:19:27then we and only then do we actually push to  production, which is like the thing that um
  1840. 2:19:30customers and and users can actually use. And so  the process is basically always just like um local
  1841. 2:19:37staging production. And this is not super relevant  for our last step, but it'll become more relevant
  1842. 2:19:44when we use things like GitHub repositories and  version control because there are changes that
  1843. 2:19:49you can make locally. other people can be working  on changes on the staging server and then other
  1844. 2:19:53people can be working on changes even on like  the production server. Although ideally you
  1845. 2:19:56don't make live changes because a single live  change can like screw up your your whole work
  1846. 2:20:00um like your whole app like you saw earlier. Uh  and then you can actually just spread it across
  1847. 2:20:04have multiple people working on multiple things  simultaneously. So that in a nutshell is basically
  1848. 2:20:08everything you guys need to know about hosting.  Um you do obviously need to pay for hosting for
  1849. 2:20:12most services like you know you're not going to  be able to sign up to hosting or or site ground or
  1850. 2:20:16whatever for free. This is basically you renting  a computer for the purposes of hosting your
  1851. 2:20:21application on it and then having users interact  with it. And obviously every time some user goes
  1852. 2:20:25to a website or whatever and there's a request  made to the host, the host consumes a little bit
  1853. 2:20:28of electricity. There's like a little bit of of  a cost back there. So they um they arbitrage that
  1854. 2:20:33and then they charge you some big multiple. And  there's like a bajillion hosts out there. There's
  1855. 2:20:36like VPS's, virtual private servers. There's like  dedicated um computers or dedicated servers you
  1856. 2:20:42could buy. There's like whole computers basically  or whole servers that you could buy. Or what they
  1857. 2:20:47do is they take one server and they divide it into  like 50 servers and then slowly partition it out.
  1858. 2:20:51There's like so many different ways of doing this  that it's not really worth us getting into. But
  1859. 2:20:54suffice to say, this is just like the basic model  of um communication. Another thing that's really
  1860. 2:20:57important to understand are databases. Now, for  all intents and purposes, like I talked about,
  1861. 2:21:01these are basically just like a Google sheet.  If you guys have ever used a Google sheet or
  1862. 2:21:04you ever used Excel or anything like that, the  best mental model I found so far is just to
  1863. 2:21:08treat every database that you use like um a Google  sheet. So, just like a Google sheet, you'll always
  1864. 2:21:13have like header row, uh, a header row, which is  basically just like the titles of every single
  1865. 2:21:19column in your database. So, in this instance,  for instance, our table, which I just move my
  1866. 2:21:24big head out of the way, is called sheet one down  here. Okay? And sheet one, okay, is just one of
  1867. 2:21:30many possible tables in our database. We can make  100 more tables if we wanted to, but they're all
  1868. 2:21:35going to be divided into like sheet one, sheet  two, sheet three, or whatever the heck we title
  1869. 2:21:38them. Now inside of sheet one um we have uh three  columns here. The first column has a header name
  1870. 2:21:44or a key of id. The second has a header name or a  key of date underscore created and then the third
  1871. 2:21:49has a a header name or a key name of value. Now  underneath this sort of initial row which just
  1872. 2:21:56defines the names of all of the various fields. Um  we then have the values themselves. And so this is
  1873. 2:22:01a database for instance that contains a one record  or one row. If I duplicated this a bunch and then
  1874. 2:22:08I don't know wrote some other IDs here because  this is going to be important. You can see now we
  1875. 2:22:12have a database um with one table called sheet one  that now consists of four rows. Okay, the thing
  1876. 2:22:18is depending on the type of database that you're  using. Okay, you need what's called a primary key.
  1877. 2:22:24And a primary key is just something that's unique,  one column that is basically always unique from
  1878. 2:22:29row to row that basically defines that row or  that record as like being super unique and not
  1879. 2:22:34existing anywhere else. And so for the purposes of  this database, the primary key is going to be the
  1880. 2:22:41ID because the ID is always going to be different  between each record. If you have two records with
  1881. 2:22:46the same ID, obviously there's a conflict. If you  think about it logically, the reason why we need
  1882. 2:22:49it structured in this way is because if we have  instructions in our server and the instructions
  1883. 2:22:53are to pull a specific record from a database and  it's like, hey, I want you to grab the record with
  1884. 2:22:58the ID 23FI23F2 and it turns out there's like 10  records like that. You'll return 10 records and
  1885. 2:23:05how are you supposed to visualize 10 records? Like  that's going to, you know, it's going to screw up
  1886. 2:23:07whatever your logic is unless you specifically  handle for that. And so these databases for
  1887. 2:23:12the most part, most people that vibe code apps  suffered using the SQL database with um separate
  1888. 2:23:16primary keys are typically organized in that way  where you have one sort of like starred column.
  1889. 2:23:21And so I'm just going to make this one the starred  column. It's the yellow one. And then these here
  1890. 2:23:24can be the exact same. Like you could technically  have 100 records all created in the same day,
  1891. 2:23:27but since they have different IDs, they're all  different records, right? Same thing with the
  1892. 2:23:30value. Okay? So just like in a Google sheet or an  Excel file, you can actually like filter things
  1893. 2:23:35out. Um you can do the same thing inside of a  database. So if I go back to our little example
  1894. 2:23:39here and then um I add a filter which I can do on  sheets really easily just using a little hotkey.
  1895. 2:23:44You can also just go to data and then you could  click on create a filter if you wanted to follow
  1896. 2:23:49along this demonstration. What you can do is  if you click on this little filter button you
  1897. 2:23:52can see that you can now just filter specific  records. Like I could for instance only grab
  1898. 2:23:57um you know this record here 23FI. Okay. And if  I did so it would remove all of the additional
  1899. 2:24:02records here and then I'd only be looking at this  data. And so every time that a server makes a
  1900. 2:24:06request to a database, that's basically what it's  doing under the hood, it's just doing this in like
  1901. 2:24:09a fully automated fashion. Likewise, I can filter  based off of fields that are not my primary key.
  1902. 2:24:13So maybe in date created, what I wanted to do is  I wanted to grab all records that have 2025-10-3.
  1903. 2:24:19So as you can see here, now I'm grabbing multiple  records, okay? But each of these have different
  1904. 2:24:22primary keys. And this is just a way that I could  filter stuff. It's just like using a search bar,
  1905. 2:24:26right? You can do the same thing for value, do the  same thing for whatever the heck else you want,
  1906. 2:24:30um, you know, in your database. So basically  every time that you send a request from you know
  1907. 2:24:34your client your browser by clicking a button  you send that request to the server the server
  1908. 2:24:38interprets it. What it's doing is it's sending  another request to a database which um you know
  1909. 2:24:42is basically just acting like a big Google Sheets  filter. Now the cool thing is there's two major
  1910. 2:24:47types of databases right now. The first is called  SQLbased. So SQLbased is divided into a bunch of
  1911. 2:24:53different popular versions. I mean really there's  like a thousand but three most popular ones right
  1912. 2:24:56now are my SQL postgrql which is probably the  most popular one and then SQLite and then you
  1913. 2:25:01also have what are called NoSQL databases like  MongoDB and Cassandra. How I've always worked with
  1914. 2:25:06the differences is SQLbased databases basically  fix the column headers and so it's always going
  1915. 2:25:13to be the same column headers for all the data  and all of the records that go into a database.
  1916. 2:25:18And so just like here we have those three column  headers ID, date created and value. Basically,
  1917. 2:25:22every single record in this database will always  have an ID because it's the primary key and can
  1918. 2:25:27optionally have either a date created or a value  or it could have both. And so, um, you know, for
  1919. 2:25:32instance, you might get something that looks like  this with a date created and then no value. And
  1920. 2:25:37that is what's called a valid record. Likewise,  you can get something that looks like this with no
  1921. 2:25:42uh, you know, obviously the IDs are going to  be different. No date created, no value. And
  1922. 2:25:45you can also have something that looks like this.  Okay? And you know as long as you have a primary
  1923. 2:25:51key which denotes that this is a separate record  um every other field is optional but it has to
  1924. 2:25:56stick to this structure. Now no SQL databases are  a little bit different in NoSQL I'm just going to
  1925. 2:26:02create a new sheet here. Basically what we have  is rather than having just like one header row up
  1926. 2:26:07at the very top I want you to pretend that every  single item in your database has its own header
  1927. 2:26:13row. And so the first record here will have ID,  date created and values. So let's say the ID is
  1928. 2:26:19this, date created is this, and then the value is  this. Okay? Or I don't know, let's just make it a
  1929. 2:26:25little bit easier. Let's just call this uh we have  a record here called first name. Probably makes
  1930. 2:26:30more sense. And then this one's Nick. So um you  know what we have here is we have one record with
  1931. 2:26:35an ID, a date created, and a first name. Well, for  the next record, instead of just like sticking to
  1932. 2:26:40this format, you could have whatever the heck you  wanted. So I'm actually just going to paste this
  1933. 2:26:44down here. And then I'll say this record actually  has um a last name instead. It has a date created
  1934. 2:26:56column and then it also has a date modified  column. Maybe this date modified as 29th. If I
  1935. 2:27:03added another record here, okay, maybe what I have  here now is I have a full name. This one's Nick
  1936. 2:27:11Sarif. Then I also have my little date created a  little bit over to the right. and maybe there's
  1937. 2:27:15no date modified. And so basically what occurs in  a NoSQL database is every single record has its
  1938. 2:27:22own data structure rather than everything being  100% fixed and looking the exact same like we
  1939. 2:27:29had with our previous uh SQL database. You know,  every record will have an ID. Then it's optional
  1940. 2:27:34whether they have date created or value. But  it's not like they could have another, you know,
  1941. 2:27:37it's not like this row could have another value  called uh first name called Nick, right? Unless
  1942. 2:27:42we explicitly define that up here as a value  or a header that exists on all. Okay. Whereas
  1943. 2:27:48this would be empty empty empty empty empty empty  empty and then this would be nick. Okay. It's not
  1944. 2:27:52like we can just add additional um features or  or types of data. In a NoSQL database you have
  1945. 2:27:58total freedom and flexibility. And it's a lot more  like like a Google Drive folder where you're just
  1946. 2:28:02storing a bunch of different documents and every  single document could look a little bit different.
  1947. 2:28:07Now, obviously for our purposes, we want a simple  way to like call a database and then retrieve all
  1948. 2:28:12records that have a first name Nick Sariah or that  have an ID of of something. Um, you know, we're
  1949. 2:28:16going to use SQL for the most part. But there are  some instances where NoSQL makes more sense. Um,
  1950. 2:28:21and if you want to look more into that, just look  for the difference between like relational and a
  1951. 2:28:24non-reational databases. Um, and then maybe  you could have your agent tell you. Next,
  1952. 2:28:28I want to chat languages and frameworks for people  that might not be super familiar with them. So
  1953. 2:28:34there are three basic languages used these days in  modern SAS app um sort of development engineering
  1954. 2:28:41and I'm going to draw them as little bubbles and  I'll show you how they all interact. The first
  1955. 2:28:45is probably the oldest which is hypertext markup  language. The next I just copy this is a little
  1956. 2:28:53bit newer and it basically took the internet from  just a bunch of ugly static web pages to pretty
  1957. 2:28:58dynamic and interesting web pages CSS. And then  the third is how we got interactivity in the web,
  1958. 2:29:05which is through JavaScript. Now, I'm not going  to give you guys a big historical lesson on each
  1959. 2:29:09of these because to be honest, I mean, I just  be googling this stuff anyway. Um, but suffice
  1960. 2:29:13to say, HTML is actually like basically the only  thing that you need in order to run a website. CSS
  1961. 2:29:20is sort of the design layer that makes things  really pretty. And then JavaScript is just
  1962. 2:29:24what allows you to build interactivity into pages  like you clicking a button and then a new element
  1963. 2:29:29appearing or something. And so to show you guys  this HTML side, if you head over to info.sern.ch,
  1964. 2:29:35you can actually see the very first website ever  made. And that website is called the worldwide
  1965. 2:29:40web. This is literally describing the worldwide  web. You know how all websites or many websites
  1966. 2:29:47have www preended? That stands for worldwide web,  which is a framework that people put together god
  1967. 2:29:52knows how long ago now. probably at least 40  years ago. And so basically this explains how
  1968. 2:29:56the internet works. Okay. Now obviously you don't  need to have gone to this website to know how the
  1969. 2:30:01internet works more uh fundamentally speaking.  I think every kid just inherently gets it when
  1970. 2:30:05they are given their first iPad with Coco Melon  on it. U no jokes aside uh the worldwide web is
  1971. 2:30:11is a website that's entirely built in HTML. And  you can see because the file ending up here is
  1972. 2:30:14HTML. If I open this up you'll see the actual code  of the website down here. And it's very simple.
  1973. 2:30:19There's a body, there's a header, there's an H1,  which stands for worldwide web, an AT, which is a
  1974. 2:30:25bunch of links, and then P tags and and stuff like  that. Now, worth noting that this is a website
  1975. 2:30:30with no CSS, which is sort of the next level up.  Now, CSS is how you change the style of the page.
  1976. 2:30:36It's how you make things bigger or smaller or  or sexier or whatever. So, if I go style here,
  1977. 2:30:43I can actually change the font size to like 300  pixels and I can make that bigger. This HTML is
  1978. 2:30:51just that core fundamental um kind of structure,  the scaffold of the page. This style is now CSS
  1979. 2:30:57and it's where I'm like applying some additional  information to change the size. I could change
  1980. 2:31:01the color and I could do so on and so forth. I  could I could change things quite a bit. Now,
  1981. 2:31:04there is that one final piece which is JavaScript.  And JavaScript nowadays is done mostly through the
  1982. 2:31:10console. Inside of the console, you can actually  run um JS. So what I could do is I could go
  1983. 2:31:15document query selector and then I could look  for all all H1's elements and then what I could
  1984. 2:31:21do actually remove this from the page um just by  clicking or writing document.query selector H1-E
  1985. 2:31:28and this is an example of that interactivity that  I was talking about. Basically with JavaScript
  1986. 2:31:32what you can do is you can I'm realizing that  my head's in the way here so you can't see that
  1987. 2:31:36most recent function. Um basically what JavaScript  allows you to do is allows you to select specific
  1988. 2:31:41elements on the page and do whatever you want with  them. You can make them bigger, you can make them
  1989. 2:31:44smaller, you can apply styles, you can create new  HTML. I mean, there's like a bajillion different
  1990. 2:31:48things you can do. Okay, so those are the three  programming languages. And hopefully we're all
  1991. 2:31:51on the same uh page about how these two or three  interact with each other. The thing is, obviously,
  1992. 2:31:57if you design a website or a web app using HTML,  CSS, and JavaScript, there's like a million
  1993. 2:32:03different ways you could do so, right? You could  write whatever website you want, apply whatever
  1994. 2:32:06styling you want, and then obviously apply  whatever interactivity you want, and that's great.
  1995. 2:32:10But the internet thrives off standardization,  which is where things are done in a repeatable
  1996. 2:32:15and sort of consistent way. Because of this,  the more standardized the internet tends to be,
  1997. 2:32:21the better solutions that people can build on top  of pre-existing solutions. And that's really the
  1998. 2:32:25whole idea of programming languages in the first  place. So in addition to this idea of you know
  1999. 2:32:30languages as um standardization you also now have  this concept of frameworks as standardization. And
  2000. 2:32:41so frameworks are a level of abstraction that  are built on top of languages. And what we do
  2001. 2:32:46is we actually just take these three sort of Lego  blocks and we just construct them in a specific
  2002. 2:32:51way essentially. Okay. And right now there are a  bunch of different frameworks out there. The most
  2003. 2:32:57popular ones I would say are next.js which is the  framework that we just used to define and build
  2004. 2:33:05our current app. And you can see that that include  a lot of that included a lot of opinionated
  2005. 2:33:10um framework based stuff for like the folder  structure and components and hooks. These are all
  2006. 2:33:15things that are basically a handme-down directly  from our framework. You also have um vit right
  2007. 2:33:21now is super popular and you'll see a lot of apps  created with vit and then on the other side you
  2008. 2:33:26also have view or really like nux.js and there are  varying levels of abstraction here like nux.js is
  2009. 2:33:32actually an it's like a second framework built on  top of another framework called uh react which is
  2010. 2:33:37kind of funny. Um nux.js is built on top of view.  Uh you know there are a lot of like dependencies
  2011. 2:33:43and stuff and if you guys remember earlier I said  we stand on the shoulders of giants. really do uh
  2012. 2:33:47because everything nowadays is built off of  something somebody else built which was built
  2013. 2:33:50off something somebody else built all the way  down to where we were programming computers
  2014. 2:33:53with little ones and zeros on pieces of tape. And  so in addition to you know our chosen tool and
  2015. 2:33:58this is the tool I'm going to be using for the  most part throughout this course. NextJS being
  2016. 2:34:03essentially the way that we coral these three  programming languages together. Nex.js JS is also
  2017. 2:34:09an opinionated framework that um you know helps  us organize things like hosting, helps us organize
  2018. 2:34:16things like how to do you know database calls and  whatnot in a standardized way. You guys remember
  2019. 2:34:22earlier we talked about middleware authentication  middleware uh has a standardized interface for
  2020. 2:34:26authentication middleware is a standardized way  to put together routes which are just the names
  2021. 2:34:31of like um website endings. So excalagger.com/ I  don't know settings that's a settings route for
  2022. 2:34:36instance and so on and so forth and what's really  cool is because a lot of people have used these
  2023. 2:34:41frameworks before you know like NexJS isn't Neo  was developed at least half a decade ago if not
  2024. 2:34:45more I built tons of projects with it before we  had the luxury of agents to do that for us because
  2025. 2:34:50of all this we had a lot of pre-existing projects  out there on the internet that were built with
  2026. 2:34:53this and these were all used in the training sets  of these large language models like you know opus
  2027. 2:34:58gemini and so on and so forth which means make  a long story short If you use a framework, you
  2028. 2:35:03usually get significantly higher quality results.  Now, frameworks obviously have some baggage as
  2029. 2:35:07well. The more opinionated things you put into uh  you know a design system or whatnot, obviously the
  2030. 2:35:14more lag that you can have, the bigger the files  can be and and so on and so forth. But for the
  2031. 2:35:19most part, these are a good balance of like  speed, stability, reliability, and then also
  2032. 2:35:23security. You know, because these frameworks have  existed for a while, people have put together some
  2033. 2:35:27pretty simple and easy ways to economize um our  security and our ability to build apps. Okay. So,
  2034. 2:35:32am I saying that you have to like go and  learn every single thing in HTML? No. CSS? No.
  2035. 2:35:36JavaScript? No. Um, do you have to read through  all the NexJS docs? No. Although they are they
  2036. 2:35:40are pretty cool if you wanted to. None of these  things will necessarily make you like a better
  2037. 2:35:44vibe coder. But I think it's important to at least  be able to like look at the Lego blocks and see
  2038. 2:35:48how they fit together because if you don't, then  you're a lot more liable to produce what I think
  2039. 2:35:52a lot of people nowadays are terming as sloop  out there on the internet, which are like simple
  2040. 2:35:54vibecoded apps that aren't really well thought out  and then interact with the rest of the internet in
  2041. 2:35:59pretty stupid ways. The last thing I want to talk  about is version control. And to make a long story
  2042. 2:36:05short, version control just answers the question,  how do I store successive updates of files on a
  2043. 2:36:13server as efficiently as humanly possible? Let me  give you a brief little example. I'm sure you know
  2044. 2:36:18back in high school or college or whatever, those  of us that have gone there in the last few years,
  2045. 2:36:23you've run into situations where, you know,  you're tasked with writing an essay. And so,
  2046. 2:36:28you know, you write your essay probably really  late in the middle of the night with a bunch
  2047. 2:36:31of Cheetos beside you. At least that's how I  used to do it. And then, um, you save it as,
  2048. 2:36:35I don't know, essay docx, let's say. You know,  it's like a it's like a Google doc or something
  2049. 2:36:39like that file. And you do it locally in your  computer, maybe Microsoft Word, okay? And then,
  2050. 2:36:44um, the next day, you know, you wake up and then  you give it to your friend, and your friend gives
  2051. 2:36:49you some feedback or something like that. Okay?  So what they do is they they download the file
  2052. 2:36:53and then they give it back to you and then it's  called essay with feedback.docex. So what you do
  2053. 2:37:00is you take that file but not wanting to lose the  previous two files what you do is when you make
  2054. 2:37:05your updates to it okay you don't save it as essay  with feedback you call it essay 2.d dox and then
  2055. 2:37:12the cycle just repeats itself three or four times  then you have essay 3.d dox you have essay 4.x doc
  2056. 2:37:20x and so on and so on and so forth until you have  essay final superfal important docx. Okay. And
  2057. 2:37:29before you know it, you know, your whole downloads  folder is a mess. I'm sure we've all probably had
  2058. 2:37:33situations like this before. Um I know, god  forbid, I I used to have situations like this
  2059. 2:37:37all the time. Now, that's for writing things like  essays. I want you to imagine instead of essays,
  2060. 2:37:43what you're doing is you're working on an app like  we're doing. You'll have app one dot whatever,
  2061. 2:37:48app two dot whatever, app three super important  final whatever. Obviously, these things can get
  2062. 2:37:53out of control really quickly. What compounds  the issue is this idea of needing to share files
  2063. 2:37:57because this super janky ass method, this could  work if it's just you and you understand how you
  2064. 2:38:01name your files and stuff. You could build like a  naming convention, right? But what if you want to
  2065. 2:38:04share this with like 20 other people and 20 people  all simultaneously need to be able to work on the
  2066. 2:38:08file that is the most updated without causing  conflicts and stuff like that and so on and so
  2067. 2:38:12forth. That's really the whole idea behind what  initiated version control. And so what we do is
  2068. 2:38:17we basically have again standing on the shoulders  of giants um built systems out there that store
  2069. 2:38:24not only the file itself but store the changes  between files and then just let you access them
  2070. 2:38:30by you know calling a little URL or something and  then pulling the file as well as a list of all the
  2071. 2:38:35changes um that have historically occurred. So  that at any point in time, you know, you could
  2072. 2:38:40download, let's say, this original file, but  then you could jump over here if you wanted to,
  2073. 2:38:43jump over here if you wanted to, jump over here  if you wanted to, jump over here if you wanted to,
  2074. 2:38:46and so on and so forth, all without just needing  to like pollute your, you know, file system and
  2075. 2:38:50stuff like that. What's more, at any point you  could also branch out and make additional changes
  2076. 2:38:54here, however much you want, called, I don't know,  new essay. And then you could share that new essay
  2077. 2:39:02uh with other people. Okay? Or what you could do  is you could make the changes here and then you
  2078. 2:39:08could actually take these changes and then merge  them with another pre-existing file to get some,
  2079. 2:39:13you know, new better essay hypothetically. Um, you  could do that with apps, you could do that with
  2080. 2:39:17essays, you could do that with everything.  People use version control to literally do
  2081. 2:39:20everything nowadays, research papers and so on  and so forth included. So the major place where
  2082. 2:39:26most version control happens now is on GitHub. And  what we do is we've taken this concept of like a
  2083. 2:39:32folder or a workspace and we've standardized it  into one called a repository. And so this idea
  2084. 2:39:38of a GitHub repository is very popular. You go  into github.com. This is what the website looks
  2085. 2:39:43like. Okay. And you can see on the left hand side  I'm signed in here. I have a bunch of different
  2086. 2:39:49um repositories. I didn't even realize, but  I have a bunch of people here that are like
  2087. 2:39:51starring my repos and stuff. That's hilarious.  Um I have a bunch of different repositories
  2088. 2:39:55here like worklog make money with make gyro  app.1c.copy.com copy.com, proposal generator,
  2089. 2:40:00and so on and so forth. And these are all  basically different projects that I've built. Now,
  2090. 2:40:03what's cool is if I click on any one of these,  okay, you can actually see every change that I
  2091. 2:40:08have made to this over the course of god knows  how long. This is basically over the course of I
  2092. 2:40:13don't know 346 different changes. If I click this  button, the wildest thing, so I can actually go
  2093. 2:40:18through and I can see literally every change I've  ever made to this thing. And at any point in time,
  2094. 2:40:23okay, I can actually open up the details and then  the code itself to adjust what's going on. I could
  2095. 2:40:30uh restart my, you know, project from here. I I  mean, I could do anything. I could share this with
  2096. 2:40:35other people really easily. Um, and so on and so  forth. So, I say this not because I want this to
  2097. 2:40:40be a comprehensive guide to GitHub. Obviously,  it isn't. I just like gave you guys a very high
  2098. 2:40:43level overview. Um, but in a nutshell, all this  is is just a way to store and and and save files.
  2099. 2:40:48And so whereas with our last couple of projects  with our portfolio site and then the um app that
  2100. 2:40:53we just built, I wasn't using GitHub for any of  it, from now on, what we're going to do is we're
  2101. 2:40:57actually going to take our big file structure  that we're developing locally and we're going
  2102. 2:41:01to constantly push it to GitHub so that we both  have like a saved version over there if anything
  2103. 2:41:05locally occurs, but also we have the ability to  um share it with others. And then services that
  2104. 2:41:10do deployment nowadays like Netlife, Versel, and  and other platforms out there, they can often just
  2105. 2:41:15pull directly from the GitHub. So I don't have to  like drag my folder in. I could just say, "Hey,
  2106. 2:41:19here's my GitHub repo." And then it'll just do all  the math and stuff for me. And then I don't even
  2107. 2:41:23have to like rebuild it on Netlefi. What I could  do is I could just push it to this repo, make a
  2108. 2:41:27couple of changes, and then Netifi will have  like a little hook that automatically rebuilds
  2109. 2:41:30the site every time a change occurs. And this is  how you get like different pipelines set up with
  2110. 2:41:34like production, staging, local, and so on and  so forth. You can also create different branches
  2111. 2:41:38branches. I guess I have one here called chest day  workout. That's pretty funny. Must have crushed
  2112. 2:41:42that chest day. Um, and then just have agents  manage like everything to do with uh with whatever
  2113. 2:41:47project you have. So, for instance, this is like a  little work log that I set up that basically just
  2114. 2:41:51like a list of things that I've done. I use it to  track my own my own work. And uh I developed this
  2115. 2:41:55in just a few minutes with uh with claude code  I think like two months ago essentially. The
  2116. 2:42:01last thing I'm going to mention here is everybody  gets a GitHub profile. And so there are a lot of
  2117. 2:42:04people out there that are have very popular GitHub  profiles. This is usually where most open source
  2118. 2:42:08lives. So, you know, if you develop a really cool  new idea or new framework or something, you make a
  2119. 2:42:12GitHub repository and then you share it with other  people and then other people can also make changes
  2120. 2:42:16and then improve it over time. Um, that's what  a bunch of really popular repos tend to do. If
  2121. 2:42:20you guys have checked out like the open claw one  and and stuff like that, that's where they were
  2122. 2:42:24getting um most of this this from. And then with  agents, what you could do is you could actually
  2123. 2:42:27just have parallel instances of like 10,000  operating in the background, constantly scanning
  2124. 2:42:32the workspace and then making micro adjustments  and edits in a very interpretable and accountable
  2125. 2:42:36way. So the future of software development is  basically that decentralized GitHub repo pushing
  2126. 2:42:40and pulling and stuff. Okay, cool. I think we've  now done enough of like the traditional software
  2127. 2:42:44engineering concepts for you guys to know a lot  more about how to build these things efficiently.
  2128. 2:42:48Um, what I want to do now is just talk really  briefly about a couple of the different ways you
  2129. 2:42:51could use agents to streamline your work. I know  we touched on this briefly with the repo stuff a
  2130. 2:42:55second ago, but I just want to zoom out a bit and  then just look at anti-gravity and look at some of
  2131. 2:42:59the the potential and the functionality there in.  Okay, so if I just go back to anti-gravity here,
  2132. 2:43:03you know, I still have that old site set up. Um,  I should be able to clear this just by going to
  2133. 2:43:07new. Um, one of the simplest and easiest ways to  multiply your ability to work on a specific repo,
  2134. 2:43:14which is just what I'm going to call our workspace  or file folders from now on, is basically just
  2135. 2:43:20running multiple different separate functions  simultaneously. And so, you know, I could say,
  2136. 2:43:26hey, do XYZ, and then I could just wait until this  whole thing is finished. And then I could give it
  2137. 2:43:31some more instructions. Hey, thanks. Let's now do  ABC. Or what I could do is I could make use of the
  2138. 2:43:38ability to start new conversations. And I could  actually run multiple of these um simultaneously.
  2139. 2:43:47So I think we're all familiar with just using the  little agent tab on the right hand side. But in
  2140. 2:43:52order to parallelize your work and then work a  lot faster, what we can do is we can zoom out of
  2141. 2:43:56a specific workspace and then actually just look  at like 3 4 5 10 100 agents working simultaneously
  2142. 2:44:01for us and then just orchestrate their actions.  This can sound pretty bonkers if it's the first
  2143. 2:44:05time you've done something like this, but this  sort of functionality is actually built into
  2144. 2:44:08anti-gravity and uh it's also built into things  like cloud code and and stuff like that as well.
  2145. 2:44:13The way you do so is with this agent manager in  the top right hand corner. So if I click the agent
  2146. 2:44:17manager, what we've done now is we've zoomed out  of a particular workspace. We actually have all
  2147. 2:44:21of our workspaces here listed on the lefth hand  side. And you can actually see every conversation
  2148. 2:44:26you've ever had inside of each workspace as well,  which is really handy. So, this one's improving
  2149. 2:44:30dashboard UX. This one's listing directories and  stuff like that. Here's a search I just said a
  2150. 2:44:34moment ago, or I'm pretty sure I just said like  do ABC or something like that cuz I wanted to like
  2151. 2:44:38have a bunch of these that I could quickly jump  through. You can see in this case just ask me,
  2152. 2:44:41hey, what the heck is ABC? What are you crazy? And  so on and so forth. This is some other thing that
  2153. 2:44:46I've developed here. This is some other thing  that I've developed. And so on and so forth.
  2154. 2:44:49So, I mean, like, you know, this is kind  of cool, right? You basically can just go
  2155. 2:44:51top to bottom and then see at a bird's eye view a  bunch of different conversations that you've had
  2156. 2:44:55with different agents. And you can do this across  workspaces. You can start new conversations across
  2157. 2:44:58workspaces. You can jump into a specific workspace  using the editor, right? Um, and so on. The really
  2158. 2:45:04cool thing though is if you go to this inbox in  the top lefthand corner, what you can see is you
  2159. 2:45:09basically get a list of all of the messages that  AI is sending you. And the reason why this is so
  2160. 2:45:14valuable and so cool is because if you make use of  the pending feature, which is basically where you
  2161. 2:45:21don't let AI do something unless you've cleared  it, what you can do is you could use this little
  2162. 2:45:26pending filter and then just have a giant list of  things that like 20 different agents are working
  2163. 2:45:31on simultaneously and then they're just like  serving you um you know the results and asking
  2164. 2:45:35you, hey, do you want me to do X, Y, and Z? Okay,  so let me show you a really quick and and simple
  2165. 2:45:39example. So earlier I had this website builder  repo, right? If I just open the editor here,
  2166. 2:45:44I had this big Gemini.MD where I was basically  showing you guys how to create a website and
  2167. 2:45:49then I pumped through like two or three of them  simultaneously. And I hid this from you at the
  2168. 2:45:53time because I didn't want you to obviously get  super overwhelmed. But if you open the agent
  2169. 2:45:57manager, okay, you can see that you can now start  new conversations in what's called a playground,
  2170. 2:46:02which is an independent workspace, perfect for  quick prototypes or following curiosity. Then you
  2171. 2:46:06actually just paste in this multiple times. So you  could start a conversation by going in, paste this
  2172. 2:46:13in, start another conversation by going in, paste  this in, and start another conversation by going
  2173. 2:46:18in, paste it in. And now in the playground side of  things, okay, you now have multiple conversations
  2174. 2:46:23that are occurring where it'll basically just ask  you a bunch of information. I'm just going to say,
  2175. 2:46:28um, choose all of this yourself, high-end SAS,  for a demo I'm making. You can just paste this in.
  2176. 2:46:38You could paste this in. You could paste this in.  And then you could paste this in. And what I have
  2177. 2:46:44now, okay, is I have multiple agents that are all  operating simultaneously and independently for me.
  2178. 2:46:51This first one here is called cinematic landing  page build. The second one here is called building
  2179. 2:46:54cinematic landing pages. And then you guys can't  see these other two, but it's cinematic landing
  2180. 2:46:57and cinematic landing. And basically what they're  going to do is presumably they're going to create
  2181. 2:47:01different folders for each of these and then build  all of these websites simultaneously in parallel.
  2182. 2:47:07Right now what I have think about it is I've  made one command up here and it's split rather
  2183. 2:47:13I've made four different commands up here but  basically what I've done is I've split and now
  2184. 2:47:16we have these agents all running simultaneously  and inside of this playground I have the ability
  2185. 2:47:21to like get a highle overview what of what um  they're all doing just by mousing through each
  2186. 2:47:26okay and you know sometimes you're either going to  run into token limits or there's going to be some
  2187. 2:47:31issue so agent terminated due to error here when  this sort of thing occurs you can reply and you
  2188. 2:47:36can also just use this agent conversation for it  to show you more or less like what it's currently
  2189. 2:47:40working on. So, you know, if I go to inbox here a  moment ago, it basically said, "Hey, like what do
  2190. 2:47:44you want me to do?" That that that was a message  that the agent sent to me asking me for approval,
  2191. 2:47:48right? I can actually just see all these things  at a very high level overview just by constantly
  2192. 2:47:52being on this page. And then essentially all I'm  doing is instead of like me being responsible for
  2193. 2:47:57shephering one agent simultaneously, sorry, one  agent through a process, I can shepherd multiple
  2194. 2:48:01simultaneously. And this is the difference between  somebody that's like building one project and then
  2195. 2:48:05somebody that's orchestrating multiple projects.  You do run into some issues with like context
  2196. 2:48:09switching, which is a productivity term that  basically applies to when you're trying to do
  2197. 2:48:12multiple things simultaneously or a little bit  less efficient at um every one individual one,
  2198. 2:48:16but it's sort of like monitoring like three or  four different CCTV uh uh pieces of footage if
  2199. 2:48:22you're like a security guard or something in a  mall. You're basically just zooming out. You're
  2200. 2:48:25watching three or four of these things and  you're stepping in anytime that a particular
  2201. 2:48:29person needs you. Alternatively, it could be like  you're a manager at some big office with a bunch
  2202. 2:48:34of cubicles that you're just walking up and down  the halls. When somebody needs you, they're like,
  2203. 2:48:37"Hey, you know, Nick, can you help me with X, Y,  and Z?" And so, in this way, you're capable of
  2204. 2:48:40orchestrating significantly more total output or  work than you would be able to do yourself. So,
  2205. 2:48:45it's really worth using hotkeys um if you  wanted to start building things in this way. And
  2206. 2:48:50uh generally speaking, believe it or not, instead  of just building one app, I will usually build two
  2207. 2:48:54or three apps simultaneously now with something  like the agent manager and an inbox. and then
  2208. 2:48:58I'll just like have them all run in parallel.  Um, the reason why is because then that way I
  2209. 2:49:02could build multiple versions and then I can  just pick the version I like the best. Once I
  2210. 2:49:05pick the version I like the best, I drop the other  ones and then I just proceed with that one. Um,
  2211. 2:49:08but yeah, hot keys are pretty important. So you  can find those just by mousing over each of these
  2212. 2:49:12buttons. So inbox is command I for instance,  uh, if you scroll down to playground here,
  2213. 2:49:17you can create a new instance just by holding  controlN. And so a lot of the time I'm just
  2214. 2:49:21jumping between new conversations and then my  inbox over and over and over and over again.
  2215. 2:49:25Um, you can also jump back to that editor like I  talked about earlier just by going command E. This
  2216. 2:49:29will jump you into the particular folder where  the conversation and kind of work is happening.
  2217. 2:49:32So this one's called glowing cosmos for instance.  At any point in time if you're operating inside
  2218. 2:49:36of this playground, you also have the ability  to um move this into a specific folder. And so
  2219. 2:49:40this is occurring right now in like a temporary  folder that uh Gemini and anti-gravity just puts
  2220. 2:49:45together anytime you do this sort of thing.  But you can also just click this button and
  2221. 2:49:48then you can select a destination folder for all  the files in your project. So I could, you know,
  2222. 2:49:53use the playground to sketch out three or four  different ones and then when I find one that I
  2223. 2:49:58really like, I could then use the um create a new  folder thing to like actually go in add a folder
  2224. 2:50:02and then just work in like a dedicated workspace.  They also have a feature called follow along with
  2225. 2:50:06agent in the top rightand corner. So if you  follow along with agent um basically it'll
  2226. 2:50:10pull you back in to what the agent is doing at  every step and then allow you to see the various
  2227. 2:50:14um you know pieces of work that that agent it's  worth keeping this page pretty clean. So, I'm just
  2228. 2:50:19going to proceed with whatever the heck it asked  me for. And then over here, now I basically have
  2229. 2:50:23these two main threads that I'm running. You can  see the same thing's occurring back here and then
  2230. 2:50:29also back here. And although kind of per unit,  it'll still take the same amount of time to get a
  2231. 2:50:34website out because, you know, this is operating  at the speed of um whatever Gemini 3.1 Pro is,
  2232. 2:50:39if you think about it, I'm technically doing four  times the amount of work um simultaneously across
  2233. 2:50:44all four. I don't usually recommend having  more than two or three of these operating. I
  2234. 2:50:49just wanted to show you guys how cool it could  be if you have four. I actually have five now
  2235. 2:50:52cuz I'm proceeding with some um agency operation  thing I did a while back. Uh just because I find
  2236. 2:50:57like your attention gets pulled away a little  too much. But um yeah, you can see here in the
  2237. 2:51:00top rightand corner because I'm following this  anytime it'll make a substantial major update. I
  2238. 2:51:03can actually see the code that it's working with  and so on and so forth. I usually don't actually
  2239. 2:51:07click that though. I just go to my inbox and then  I seem you know do you need anything from me? if
  2240. 2:51:11there's any specific feature or whatever that  they want, then I can I can jump right in. So,
  2241. 2:51:15let me run this for a couple more minutes, get  a bunch of websites, and I'll just show you
  2242. 2:51:17what they all look like. Okay. And our landing  pages are now starting to um be finished. So,
  2243. 2:51:22we could actually access the Vit server. This  one's using a different framework called Vit that
  2244. 2:51:26I covered earlier just by pasting this in. You  can see we now have one of the websites. Now, I
  2245. 2:51:31should note that this looks pretty similar to the  1se secondond copy website I had set up because
  2246. 2:51:35uh I think I just asked it to build something that  was like very very similar visually speaking. So,
  2247. 2:51:38we had that little heartbeat. we have this little  thing, but you know, I'm like trying to build
  2248. 2:51:41it with a particular template, right? So, I'm  just going to instantiate a bunch of versions
  2249. 2:51:44of this template, and if I like them, then I'll  go with that. This second one here is done. Um,
  2250. 2:51:48because I didn't specifically say, "Hey, I want  you to run the server and then open it." You know,
  2251. 2:51:51this one's asking me to do this terminal command,  npm rundev. Um, so I'm just going to have it do
  2252. 2:51:56it by saying run it and then it'll open it  for me and then I can take a peek. Here it
  2253. 2:51:59is. Let's copy this over. Paste this in. Cool.  And now we have another one called Aether Core,
  2254. 2:52:04which is very clean. I really like this one. Damn,  that's really, really sexy. You know, there are
  2255. 2:52:09some issues here with some of the fonts and stuff,  but hopefully you guys see like I was capable of
  2256. 2:52:12generating four of these simultaneously. This one  here is still under development. As you can see,
  2257. 2:52:17there's a hero section and it's scrolled down, but  it is running live on a server and it does have
  2258. 2:52:20that cool little bar up top. And this one here had  probably my perfect instantiation or my favorite
  2259. 2:52:25of like this slow scrolling card like that to me  looks really sweet. Um, it's just rerunning it
  2260. 2:52:29because it's making some additional changes, but  yeah, pretty cool, huh? So, you can actually build
  2261. 2:52:33multiple apps simultaneously. And in this case,  you know, I gave it some pretty static resources.
  2262. 2:52:37And I was like, "Hey, I want you to use like  this kind of noise layer in the background and
  2263. 2:52:39stuff like that." You could also just have all  of them be different. And the way you do that
  2264. 2:52:42is you just provide like a prompt that has some  inherent randomization. Basically says, "Hey,
  2265. 2:52:46I want you to randomly select like, I don't know,  a background from this online background service."
  2266. 2:52:51And then it'll use different backgrounds. Hey, I  want you to automatically select a different type
  2267. 2:52:54of style using this thing. You know, instead of  high-end SAS, I just want you to come up with a
  2268. 2:52:58different one every single time. And then it'll  come up with like a 100. So yeah, in this way
  2269. 2:53:01I've I've uh successfully built something like  15 websites simultaneously at the same time. I
  2270. 2:53:06found like the top two or three that I like. I've  proceeded with those. I filtered out the ones that
  2271. 2:53:10I didn't and then I've had like a really really  high quality product. And I've done all that stuff
  2272. 2:53:13in like 10 maybe 15 minutes or so. Um obviously be  careful with token usage here because it's always
  2273. 2:53:20going to be a trade-off between the time it takes  to build something and the total cost on your end.
  2274. 2:53:24This is just a pretty straightforward money for  time trade, but running multiple agents in this
  2275. 2:53:28way um simultaneously can be pretty cool.  Okay, now that you guys know more or less
  2276. 2:53:31everything you need to know about both modern  software development, um, hosting, databases,
  2277. 2:53:35frameworks, and all that stuff, plus how to use  agents to pour fuel onto the fire, let's build
  2278. 2:53:40product number three, which is a lead generation  SAS app that scrapes, enriches, and even queue up
  2279. 2:53:44um, the sending of fully automated emails. This  is very similar to a structure that I use in
  2280. 2:53:48production myself in my own business, Leftclick.  We work with multi-billion dollar portfolio
  2281. 2:53:52companies and essentially connect to the outbound  systems on a team to help them send emails,
  2282. 2:53:56scrape uh contact details, and then personalize  outreach at scale without needing like a million
  2283. 2:54:01bajillion hires in order to do all that for us.  So this time, instead of just diving right into
  2284. 2:54:06the app development via prompt, I wanted to take a  few moments to sketch out what an actual app might
  2285. 2:54:11look like. And there are variety of different  names for this sort of thing. Um, in my case,
  2286. 2:54:15I'm just going to call it planning. You could  call it some form of like UX or site design
  2287. 2:54:19or navigation design or whatnot. In short, um I  know for sure this app is going to need a landing
  2288. 2:54:25page. So here I just said landing page sexy on  it. We're going to want some navbar, some main
  2289. 2:54:31value proposition, a social proof section, some  how it works section, some case studies, a CTA,
  2290. 2:54:37and then a footer. This is pretty standard, right?  It's basically the exact same thing that we did
  2291. 2:54:41with Content Orb. After that, we're going to want  some sort of login and/or signup page. And so this
  2292. 2:54:46is the O form in Superbase where you enter your  email, enter your password, and then it signs you
  2293. 2:54:50up. Now, what I imagine will probably happen after  is once you're signed in, um, we'll need some form
  2294. 2:54:57of configuration page cuz I want this app to be  able to be usable by people like you, people that,
  2295. 2:55:02um, you know, I don't want to have to necessarily  build for. Instead, I want there to be a space for
  2296. 2:55:05your instantly API key, your anthropic API key,  your OpenAI API key. Uh, I want you to be able to
  2297. 2:55:11configure the prompts that are being used by the  AIS to do personalization as well as have defaults
  2298. 2:55:15and stuff like that. And basically, I just want  that to be like your onboarding. It's like, hey,
  2299. 2:55:18do you want to get started with the scraping?  Just enter your API keys here. And there are a
  2300. 2:55:22couple of other API keys that I'm going to need,  actually. But, um, in addition to that, I also
  2301. 2:55:26want like brief little one-click guides to show  people how to do all of those things. And then
  2302. 2:55:30finally, I want the actual scraping page itself,  which is just going to be a form where you put in
  2303. 2:55:34some basic parameters. And the way this is going  to work, for those of you guys that don't know,
  2304. 2:55:37there's a scraping service out there called  Appify. And we're basically just going to wrap
  2305. 2:55:39around Appify. If we can't find enough leads, then  we're going to scrape Google Maps. And then we're
  2306. 2:55:45basically going to combine both of these into some  sort of like enrichment personalization flow. Um,
  2307. 2:55:50and assuming that, you know, we've enriched and  personalized, which, you know, may not necessarily
  2308. 2:55:54mean something to you guys if you guys aren't in  the marketing space, but I'll run you guys through
  2309. 2:55:57it all um throughout this demo, then you'll just  get all the leads that you just scraped in a
  2310. 2:56:01simple CSV with some additional column that has AI  based personalization. So, we're going to need the
  2311. 2:56:07first name and email at minimum. And then I think  the last thing to talk about is that orders page
  2312. 2:56:10or just going to be like a like a history page  where you could see all the orders that you've uh
  2313. 2:56:14scraped and sent before. And then maybe I'll also  do plus specific order pages for each that have
  2314. 2:56:20like I don't know a bunch of descriptions on them.  Okay. So, you know, I think uh probably a real UX
  2315. 2:56:25designer would crucify me uh in terms of the ways  that I've laid all this stuff out, but you know,
  2316. 2:56:29seems to work pretty reasonable for me. Um, what  I do next is I basically just take a screenshot
  2317. 2:56:33of this and then I always have this on hand  cuz you know I want to like know what my app's
  2318. 2:56:38going to look like. Then I go into anti-gravity  and then what I do is I um say something like,
  2319. 2:56:41"Hey, I'm making an app that helps people scrape  leads. Turn this into a brief description of an
  2320. 2:56:45app that includes all the important components  and I actually just screenshot and I send it to
  2321. 2:56:48them." This is back when I had it like vertical.  I've since made it horizontal. Then scrolling down
  2322. 2:56:53a little bit, you can see we've now changed  it into the description. Okay. And then over
  2323. 2:56:56here we have the updated description with just a  bunch of, you know, plain text language here. So,
  2324. 2:57:01we're probably going to need more. I mean, like,  it's not that big of a deal. Then I made a couple
  2325. 2:57:05of changes and I said, "Hey, here's some scrapers  that I want you to wrap around." Okay. And now my
  2326. 2:57:09claw code instance has generated this prompt.  So, that's good for now. What I want to do next
  2327. 2:57:13is open a new folder cuz I've copied this and I  want to call this lead scraping SAS. I'm going
  2328. 2:57:18to create and I'm going to open. Now, in our  anti-gravity instance, we have a plain folder
  2329. 2:57:22here, lead scraping SAS. And so what I want to do  next is two things. First, I'm going to need to
  2330. 2:57:29feed in that prompt. And second, I want to feed  in um a description, sorry, an example that we
  2331. 2:57:34could use to basically inspire Gemini. Now, I went  on dribble and I found something that looks like
  2332. 2:57:39this. This looks pretty reasonable to me. Um keep  in mind like the design and stuff like that is
  2333. 2:57:43pretty sleek, but obviously they have a lot more  components here. Data transfer. I mean, I don't
  2334. 2:57:47really know why I would ever need a data transfer  component, but you know, there's like a bunch of
  2335. 2:57:50buttons here and stuff. And I think we could make  this work. Um, you know, our graph may not look as
  2336. 2:57:55nice, although I think we could actually make it  look as nice if we really wanted to. But for now,
  2337. 2:57:58I'm just going to copy this image. I'm going to  go back over here. I'm gonna start by pasting that
  2338. 2:58:02in. Okay. So, we're going to start just by pasting  in um this image. It looks like we're copying
  2339. 2:58:08this, but it's not actually making it all the  way to our dashboard. It's kind of annoying. So,
  2340. 2:58:11I think I'm going to have to take a screenshot  of the actual app itself. I think sometimes
  2341. 2:58:14Dribble does like anti-creenshot protection or  something. Keep in mind that we're not stealing
  2342. 2:58:19this or anything. We're just going to use this as  like inspiration. That's all. go back here, paste
  2343. 2:58:22that in. Then I'm going to say um I'm going to  head over to Google, say cold email lead scraping,
  2344. 2:58:28and I'm just going to find some links here.  Basically, I just want like a brief description
  2345. 2:58:32of what cold email lead scraping is. So, let me  see if maybe instantly has some information on
  2346. 2:58:35their site. Um, this is like a full endto-end cold  email sending platform. Uh, probably not what I
  2347. 2:58:44want. I just want like some lead scraping.  This looks pretty good. I like this. So,
  2348. 2:58:49I'm just going to copy this. I'm going to head  back here. I'm going to paste this in. I'll say
  2349. 2:58:53this is an example of the sort of thing that we're  about to build. I'm going to paste this in just so
  2350. 2:59:00it has context and so it can write my landing page  for me. And then next up, obviously, we need that
  2351. 2:59:05um prompt that we just copied over. I'd like  to build an application. I want it designed
  2352. 2:59:09according to the screenshot that I sent over. The  specifications and the stack is um in the middle.
  2353. 2:59:15And then I've also given you a description of  another website that does something similar that
  2354. 2:59:19I'd like you to emulate for the copywriting  and content and so on and so forth. Okay,
  2355. 2:59:25we're going to stick that in. And uh this is most  likely going to end up using like a next.js stack,
  2356. 2:59:30although I did not this time necessarily want  to be opinionated cuz I wanted to see what the
  2357. 2:59:34app was going to do. Uh when it ends up creating  files, it'll do so over here. Keep in mind that
  2358. 2:59:38we are in planning mode as per usual. So that's  what's going on down here. And it looks like we're
  2359. 2:59:42using Oh, actually we're using Vit, which is good  because that'll give us a the ability to maybe
  2360. 2:59:47use a different framework here. To be honest, I  don't really care about the specific framework,
  2361. 2:59:50right? We talked about how there were multiple  uh in the previous section. So, whatever works
  2362. 2:59:54is going to work. Um, you know, as long as it's  fast and performant. Okay. So, at this point, I'm
  2363. 2:59:59just going to sit back and let it do its thing.  Awesome. So, I just got a notification saying that
  2364. 3:00:02it's done for Leadzo, which is the name that uh I  decided I would give our cute little app. And now,
  2365. 3:00:08what I'm going to do is I'm going to say run  it. The reason why I'm going to do that is
  2366. 3:00:11because in order to access this application,  we're obviously going to need like some server
  2367. 3:00:15running at the back end. Our browser is going to  end up being the client and then that's how we're
  2368. 3:00:19going to communicate with that. So, our server  is going to be on our computer for now since it's
  2369. 3:00:22all local. Let's see how it goes. So, we got the  Vit server set up. This is the landing page. Uh,
  2370. 3:00:27super clean. I like it. Okay, so we have like  some weird spacing here. That's fine. This is
  2371. 3:00:33really nice. I like this AI personalization  prompt. Very clean. Very clean. Nice. 100
  2372. 3:00:38free credits. Okay. So, what happens if I click  get started? I go over here, which is nice. Um,
  2373. 3:00:44I'm just going to ask it. Oh, it looks like it's  actually recording a browser session of me testing
  2374. 3:00:49this. This is wild. It's Nick Nikki Wiki. Then,  Nikki Nikki Nikki. Let's sign up. Okay, we're now
  2375. 3:00:57inside. We have some workspace settings on the  lefth hand side here. API integrations. On the
  2376. 3:01:02right, we have some prompt engineering. So, define  the rules leader should follow and generating the
  2377. 3:01:05personalization column for each lead. Cool. Does  this actually fill in? Okay, we just have some
  2378. 3:01:10placeholders for now. What happens if um Cool. So,  it went it actually went it found the uh specific
  2379. 3:01:15API keys and stuff. That's fine. Scrape leads. So,  we need a job name, LinkedIn Sales Navigator URL,
  2380. 3:01:21max leads, then default icebreaker. I think what  we want is basically are going to want to be able
  2381. 3:01:27to just say uh I don't know like HVAC companies in  the United States and then we want it to actually
  2382. 3:01:35go and find that for us. We're not going to need a  LinkedIn sales navigator URL because the appy the
  2383. 3:01:39specific service that we're using doesn't actually  um use that. So, it's going to be okay. Then here
  2384. 3:01:43we have some fake order history which looks  really clean. We can, you know, open it up in
  2385. 3:01:46a new window or whatever. Awesome. Awesome. Cool.  So, let me just check the bottom. You guys can't
  2386. 3:01:51see this, but there's a little button that says  log out. So, click this log out button. Nothing's
  2387. 3:01:54going to happen since obviously we don't have  the off set up. Yeah. I mean, like in a nutshell,
  2388. 3:01:57this is more or less what I what I wanted. Um,  anything else that we need? So, new scrape job
  2389. 3:02:01orders configuration. I think that's basically it.  Now, now what we have to do is we basically have
  2390. 3:02:06to test this. Uh, cool. So, what I'm going to do  next is I'm just going to run through a couple of
  2391. 3:02:11these services that we're using just so we're  on the same page. Otherwise, I think it'll be
  2392. 3:02:14kind of intimidating for you guys to see what I'm  doing. But in reality, most apps nowadays are just
  2393. 3:02:19like wrappers, as in they just wrap functionality  around some other app. Of course, you could build
  2394. 3:02:23your functionality yourself if you really wanted  to, and I can help you with that. But in my case,
  2395. 3:02:27you know, for the purpose of this demonstration,  I'm just going to do what I normally do,
  2396. 3:02:30which is I use a three a thirdparty service called  this leadsfinder on a uh which basically allows
  2397. 3:02:34you to put in some parameters and then get some  leads. So, it generates targeted B2B contact list
  2398. 3:02:38using advanced filters. Now, this isn't the best  lead scraping service out there. I should note
  2399. 3:02:42that like it's actually quite poor in terms of  quality now because uh the leads are cached and
  2400. 3:02:46they haven't been around for quite a while. So,  I use this as an example in Make Your School,
  2401. 3:02:51my community all the time. But, let's say I'm  scraping some dental clinics in Canada. I want
  2402. 3:02:54to scrape a thousand. What I do is I basically  just put in a bunch of job titles here. Owner,
  2403. 3:02:57practice owner, principal dentist, lead dentist,  so on and so forth, and then locations to include,
  2404. 3:03:03which in my case is Canada, locations to exclude,  what sorts of emails I want to get. So, validated,
  2405. 3:03:08not validated, unknown. So, I I actually just want  validated emails, what sort of company website if
  2406. 3:03:13I have them. Um, we can use to narrow down the  search. The size of the uh resulting company,
  2407. 3:03:19so 1 to 10, 11 to 20, 21 to 50. the industries  that I'm looking in. So, health, wellness,
  2408. 3:03:24and fitness, hospital, and healthcare. And then  which ones not to look for some keywords, dental,
  2409. 3:03:28dentist, and then I'm also excluding some down  here. Then we have revenue, and we also have some
  2410. 3:03:32funding. So, let me just make this smaller because  I just want to show you guys how this actually
  2411. 3:03:36works in practice. I just click save and start.  And basically, this thing goes on this service,
  2412. 3:03:40Appify, and then goes and it scrapes it  for like some small little piddly fee. So,
  2413. 3:03:44it's cooking up some data magic. Uh, let's just  wait until we see the very first result, which
  2414. 3:03:49should be about 100 leads or so. And as we see  the first rung here has found a bunch of different
  2415. 3:03:53leads from specific companies, company websites,  LinkedIns, their full names, their job titles, and
  2416. 3:03:58so on and so forth. This is pretty cool, right? I  mean, this is just like a service that I'm using,
  2417. 3:04:01and it returns a bunch of leads. And so, for  the purpose of this demo, I'm going to assume
  2418. 3:04:04we're only using like simple services like this.  We're not actually rebuilding the wheel. Although,
  2419. 3:04:08I should note that you totally could rebuild the  wheel if you wanted to. It's just uh, you know,
  2420. 3:04:12it's not super easy, right? Like, this is really  the moat nowadays. It's not the app interface
  2421. 3:04:16that you build. Sorry, that's the wrong one. Uh,  where are we? right over here. Okay, so basically
  2422. 3:04:22in order to run this, right, logically what we're  going to need is we're going to need an API token
  2423. 3:04:26and then what'll happen behind the scenes is this  Appify API token will plug into this search. Okay,
  2424. 3:04:32then it'll use some data with an input like  this via API and then it'll find us a bunch of
  2425. 3:04:39of stuff. And then on the back end, we're going to  do is we're going to enrich emails using a service
  2426. 3:04:44like this. Basically, not all of the emails  that come from this service are going to have
  2427. 3:04:48um like all of the information laid out. So, we  can actually use another service called an email
  2428. 3:04:52finder to enrich that. And then over here, um  we're going to pass in either our open AI key or
  2429. 3:04:57anthropic API key, whatever one works, honestly,  and then use that to generate personalized
  2430. 3:05:02snippets of text that basically are going to allow  us to personalize the emails that we send. So,
  2431. 3:05:08hopefully we're all now on the same page.  This is a pretty niche service, but you know,
  2432. 3:05:11the best SASes do tend to be pretty niche and um  you know, that's more or less what we're putting
  2433. 3:05:15together. We also have an instantly API key for  one-click campaigns, which are basically where
  2434. 3:05:20we'll just upload the leads automatically. I  don't actually know if I'm going to do this
  2435. 3:05:23cuz the instantly API had a bunch of issues last  time I tried, so I might not. And then over here,
  2436. 3:05:27we have the actual prompt engineering. You know,  I want to generate like a highly personalized var
  2437. 3:05:32uh uh email, right? I want to say like, "Hey Pete,  been following you for a long time. I love what
  2438. 3:05:35you're doing at XYZ company." because those emails  that I send when they're highly personalized
  2439. 3:05:39like that tend to land a lot better. So here's  where you can actually define the prompt that
  2440. 3:05:43we're going to use inside of the app in order to  generate these ice breakers. So you're an expert
  2441. 3:05:47sales SDR. Your job is to create a highly relevant  one or two sentence icebreaker so on and so forth.
  2442. 3:05:50This is this is everything here and the idea is  you'll get to change this over time and then you
  2443. 3:05:54know save and then see your new orders and stuff  like that. Okay, so hopefully now we're all on
  2444. 3:05:59the same page and I've created this demo. This  is basically like the vision of the app. What
  2445. 3:06:02I'm going to do now is I'm going to go through  and just make a bunch of changes. Um, I'm also
  2446. 3:06:07going to feed in like the API documentations or  the services that I want to scrape and use. And
  2447. 3:06:10then my agent should do a pretty good job to  start. This is great. The Appify scraper that
  2448. 3:06:17I'm using to generate leads doesn't require a  LinkedIn sales navigator URL. I'll give you the
  2449. 3:06:22Appify API below as well as everything that  you need in order to make this request, but
  2450. 3:06:27you'll have to modify the new Scrape job form to  reflect that. What we'll do is we'll pass in a job
  2451. 3:06:33name and then we'll have AI convert that job name  into a list of filters that work with the specific
  2452. 3:06:40um Appify scraper that we're using. We also need  a way to be able to click into the orders under
  2453. 3:06:46order history and then open them in sort of a  sidebar. Also, right now nothing happens when
  2454. 3:06:50I click those three little dots or the download  button. Obviously, we're going to need to download
  2455. 3:06:54these CSVs. Under the configuration section, let's  start with the Appify API token up at the top.
  2456. 3:07:01Then let's do the Anthropic and OpenAI API tokens  underneath. And then let's remove the instantly
  2457. 3:07:06API token completely and have the any mail finder  down below. The idea is going to be our Appify
  2458. 3:07:11actor is going to return most of the information  that we need rather than treat OpenAI's API key
  2459. 3:07:19as a fallback. Let's just treat it as another  option they could go through and then let's
  2460. 3:07:22just prioritize anthropic. For instance, if both  the anthropic and open AI API keys are filled out,
  2461. 3:07:28the model should automatically choose anthropic.  If anthropic is empty and open AAI is uh present,
  2462. 3:07:33then we should automatically choose open AAI.  And we'll just proceed in that manner. And then
  2463. 3:07:37for prompt engineering, I'm actually going to  give you a big long prompt that you could use to
  2464. 3:07:41significantly improve the quality of the output. I  want you to incorporate this. Once we're done with
  2465. 3:07:46the front end, we obviously need to work out the  back end and have all these functions available.
  2466. 3:07:51So, what I'm going to do is I'm going to create  av and then I'm just going to paste in all my
  2467. 3:07:54API keys for you so that you have them. You  can use this as demos to basically test the
  2468. 3:07:58backend functionality and we could use these  and store them um in a static database for now
  2469. 3:08:03just in like JSON files or or whatever. When we  eventually push to our database and use superbase
  2470. 3:08:09um then we can make these more dynamic. I think  you have everything that you need. If you have any
  2471. 3:08:14uh questions or misunderstandings or  whatever, just give me a shout. Cool.
  2472. 3:08:17So now I'm just going to go through and then give  it everything that I promised. So the appy API is
  2473. 3:08:23going to be here. It's going to go right into  the app API docs. Now what we want is we want
  2474. 3:08:30to run the actor synchronously with the input and  return the output. I believe return the data set
  2475. 3:08:40items rather. So I'm just going to see if I could  copy this whole page. Can I copy this whole page?
  2476. 3:08:45Sometimes Appify has the ability to copy the whole  page for AI. Yeah, it does. So, copy for LLM.
  2477. 3:08:50Paste that in. See how long that is? That's super  long. Yeah, it's pretty long. And then I also want
  2478. 3:08:57to paste in the specific stuff about the actor.  So, this is the specifics about the actor. Input
  2479. 3:09:05schema for actor is here. And then, um, I also  promised that I'd feed it in a big long prompt.
  2480. 3:09:14So, I'm going to go over to Maker School wrapped,  which is massive document that I put together that
  2481. 3:09:19basically guides everybody through how to write  like super high quality cold emails. And then I
  2482. 3:09:24have a little prompt here that actually you guys  could use as personalization. So, what I'm going
  2483. 3:09:29to do is just going to type personalization and  start down at the bottom. There we go. And this
  2484. 3:09:37is going to be the prompt which I'm going to feed  in right here. Here's a personalization prompt.
  2485. 3:09:46For the personalizations, use Claude Sonnet 4.6  or uh uh GPT 5.3. Check out both of their docs.
  2486. 3:10:00Okay. And then I think that has everything  that I told it that I would give it. I mean,
  2487. 3:10:04this is pretty long, right?  Just make sure. Okay. So,
  2488. 3:10:06I'm going to create av and then um paste in  all my API keys for use. That makes sense.
  2489. 3:10:12So I'm going to go over here and then just go env.  And then I'm now going to go find a bunch of API
  2490. 3:10:17keys on all the services that I promised it and  then just paste them all in. So this is going to
  2491. 3:10:21be my enthropic API key right over here. Then go  apply API key. So I head over to appy, go to my
  2492. 3:10:29console. There's always a way for us to grab our  API key from whatever service we're using. So I'll
  2493. 3:10:37go up here to API and integrations. We'll create  a new personal API token and I'll call this for
  2494. 3:10:42SAS app. Should I limit token permissions?  Should I set the expiration date? H yeah,
  2495. 3:10:49I'll set an expiration date just in case I forget  to delete it. Okay, this one's expiring tomorrow.
  2496. 3:10:54That's all good. I'm going to copy this now. Paste  that in. Uh I need my open AI AP. Actually, do I
  2497. 3:10:59need my open APK? No, I don't because I'm going to  use the anthropic one. Ah, I suppose uh the other
  2498. 3:11:04services that I need, I can find them by looking  at my Vit app right here. Any MailFinder API key,
  2499. 3:11:15paste that in. So, we'll go to any mailfinder,  log in. I'm going to go up to the API and I'm
  2500. 3:11:20just going to copy this token right now. Go back  to anti-gravity. Feed that in. And we should now
  2501. 3:11:24have everything. So, I'm going to press enter. And  I think this is now going to be able to develop
  2502. 3:11:28the rest of our app, at least for now. Uh, this  is going to be like kind of what we see above the
  2503. 3:11:34fold. Let me just be smart about this. Don't  just paste the prompt in verbatim to the user
  2504. 3:11:38editable section. Obviously, it's pretty long. All  right, we've made a couple of changes here. Now,
  2505. 3:11:43we have find me VP sales and practice owners at  dental clinics in Canada. I want companies with 11
  2506. 3:11:47to 50 employees. That's kind of cool. If we go to  orders here, can we actually click on these? Yes,
  2507. 3:11:51we can. As you can see, we now get a little  sidebar. Um, the sidebar is kind of small,
  2508. 3:11:55so I'm going to adjust that in a second, but  it is still pretty neat. I mean, I can click
  2509. 3:11:58the download verified CSV button here. So, it's  pretty nice. I like this. I really like the fact
  2510. 3:12:02that we have this little job. It also pumps up so  quickly. It just makes it seem really snappy. And
  2511. 3:12:08here is the prompt engineering. So, the prompt is  just pasted entirely in now, which is nice. Yeah,
  2512. 3:12:14it's basically perfect. We do have um what looks  to be no training examples, but that's okay. These
  2513. 3:12:20prompt variables are going to be injected as  the first name to lead, last name of the lead,
  2514. 3:12:22headline, industry, organization name, location,  even their email address. That's going to be cool.
  2515. 3:12:26And then we also have our uh our tokens in. So  now it's just time to actually give this a try.
  2516. 3:12:29So I've just added the API keys right over here as  mentioned. And now we're basically good to go. I'm
  2517. 3:12:35going to wait for this thing to relaunch the dev  server and then we're actually going to test out
  2518. 3:12:39the flow. I should note that, you know, because  we are testing out what is essentially going to
  2519. 3:12:44be the core function of our app, just like with  a full stack app, like the probability it'll work
  2520. 3:12:48on the first try is pretty low. I found it kind  of interesting because a lot of people like they
  2521. 3:12:52judge AI by its ability or inability to do things  in one go. uh human beings rarely do things in one
  2522. 3:12:57go as well. The difference between humans and  AI models is silicon thinks at something like
  2523. 3:13:0110,000 times the speed. So you could just try  it 10,000 times faster. So you know whether or
  2524. 3:13:06not this works in one shot is okay. We're just  going to go back and forth until it it works
  2525. 3:13:10reliably. Um and then from there we're going to  pump this up to netify just like I had before.
  2526. 3:13:14And then app number two, full stack app number  two, but total uh web app number three is going
  2527. 3:13:21to be completely cool. I've just done this. Now  it's storing what's called local storage since
  2528. 3:13:24of course we're always doing our our first jobs  uh or our first check statically. So let me exit
  2529. 3:13:29out of my cloud API keys. Thank you very much.  Go right over here. Just relogged in and then
  2530. 3:13:34I'm just going to go scrape leads. So I'm going  to say and I imagine there are going to be some
  2531. 3:13:37issues here. Find me VP sales at dental clinics in  Canada. I want companies with 10 employees. Okay.
  2532. 3:13:47And why don't we do I don't know 200 leads. And  then we'll go laconic or lassic. I don't actually
  2533. 3:13:54know how to say that. Um and then we'll go error  executing leads workflow. Check console. I'll head
  2534. 3:14:00back to console and then I see that we now already  have some issues not found. So what I'm going to
  2535. 3:14:06do is I'm just going to scroll through this then  feed back to our agent. All right. After some
  2536. 3:14:13back and forth, it's now telling us it's good  to go. I'm not entirely sure if this is true,
  2537. 3:14:17but we are going to give it a try together. Uh,  I think it'll probably be over here. And then I
  2538. 3:14:22go slash scrape. Find me some practice owners at  dental clinics in Canada. One to 20 employees.
  2539. 3:14:30Cool. I'll press 100 max leads. We'll run the  workflow. We see here it's now doing what it's
  2540. 3:14:35saying is a search extraction. And it looks like  it hasn't finished it successfully successfully
  2541. 3:14:41because we're immediately getting a return  saying it's it's completed successfully,
  2542. 3:14:45but it isn't. Let me just paste this back. I  ran this on localhost 888/scrape returned this
  2543. 3:14:52and then I'm just going to paste it in. I'm also  going to uh paste in my um input as well just so
  2544. 3:14:59that I could, you know, monitor this and also  maybe have a little bit more meaningful of a
  2545. 3:15:03back and forth. Um but anyway, let's see what it  has to say. just as a form of parallelization.
  2546. 3:15:09While this is debugging whatever the appy issue  is that's leading to um inconsistent output,
  2547. 3:15:14I'm actually just going to have it adjust  the copy on the landing page as well. So,
  2548. 3:15:18let me see here. Hey, this is fantastic. I'd like  you to change the copy on the landing page that
  2549. 3:15:24it's a little bit more geared towards outbound  cold emails specifically. Um, also there are some
  2550. 3:15:31minor graphical issues like the start for free  buttons arrow is on the same is on a different
  2551. 3:15:36level than the text. I'm also seeing that there  are four cards under built for performance,
  2552. 3:15:42but the fourth spills out onto the second row.  Let's do six cards instead. The main value
  2553. 3:15:48props here are the breadth of contacts, the high  quality database, the high quality of enrichment,
  2554. 3:15:55um the simplicity of the tool, the affordability  of the leads relative to most other people. For
  2555. 3:16:04the AI personalization section, um under AI  personalization prompt, remove the export to
  2556. 3:16:11oneclick instantly campaigns and then change  the language so it's not start for free.
  2557. 3:16:17You just start. I'm also noticing that there's  no pricing section. Update it so that there is a
  2558. 3:16:21pricing section. And make sure that everything in  the navbar is like perfectly centered. Right now,
  2559. 3:16:26it's a little bit off, or at least it seems to be  off. Add a pricing section that is on average 0.05
  2560. 3:16:35per credit. Every credit returns one verified  email. And then offer some higher and lower plans
  2561. 3:16:42um that scale with price. Obviously, when  you purchase more, you should get more of
  2562. 3:16:46a discount. Cool. So, I'm going to pump that in.  And then I'll say only modify the landing page.
  2563. 3:16:52There are other agents currently working on other  sections of the website. Do not modify anything
  2564. 3:16:56that is not the landing page. Also, don't you  don't need to rebuild. Okay. So, I'm going to
  2565. 3:17:00have that operating at the same time as our other  tool, which is fixing the appy scraper. And then
  2566. 3:17:06I can monitor this just by going back to command E  and checking out the agent um kind of conversation
  2567. 3:17:12here. If I go to under inbox, you can see my  two open conversations. There's this one here,
  2568. 3:17:16and it looks like we're still building or fixing  whatever the specific Appify problem was. Looks
  2569. 3:17:21like it has to do with like hash IDs or whatnot.  Okay, so this is a good summary of where it's at
  2570. 3:17:25right now. And then the landing page copy  builder is now doing some things. Cool. So,
  2571. 3:17:31it's analyzing the landing page. And now it's  going to go through and actually write it.
  2572. 3:17:36Looks like this search worked now on the uh  curl command that it created and it just did
  2573. 3:17:42this to validate without me actually having to go  through and then do it all myself on the website.
  2574. 3:17:46It's also reporting the specific issues. So there  was some location, some swallowed exceptions and
  2575. 3:17:51so on and so forth. That's cool. And it also ran  the live test and it's asking me to do it again on
  2576. 3:17:56um you know 888. So that's a different server.  Then I'll go what are we doing? Scrape. return
  2577. 3:18:03me owners of HVAC businesses in Texas. Okay, we're  still getting the zero completed. So, let's go and
  2578. 3:18:11debug Y. This is my input. Just go into the new  landing page update. We've now changed this to six
  2579. 3:18:17rows, which is cool. This looks kind of silly.  So, I'm just going to go back here and say is
  2580. 3:18:23currently on three lines. The on though the N  looks odd. Everything else here does look pretty
  2581. 3:18:32solid though. I like that we now have a growth and  pricing plan with the same style. 49.99 and then
  2582. 3:18:40249. Super cool. And I'll just say let's dress  up that final CTA card down at the bottom. Cool.
  2583. 3:18:51We'll go back to our appy scraper, see how this  is going. Just shut over a request here. And it
  2584. 3:18:55looks like we are actually doing something which  is nice. Um, normally this would have immediately
  2585. 3:19:01errored out, but it's either hanging or it is  doing what I asked it to do. I think this is hung,
  2586. 3:19:06which is why nothing is occurring. If I  refresh this, I think the server probably
  2587. 3:19:10went down halfway through. The good news is we  are populating the database, although either
  2588. 3:19:14some design issues have occurred or something  is broken. But as you can see here, we have the
  2589. 3:19:19status, the date, and then the verified emails as  well. I'm seeing no problems in the configuration
  2590. 3:19:24side as well. So, it really is just the scrape  leads hangup. What I think I'm probably going to
  2591. 3:19:28do given that this has taken me like 10 minutes or  so just behind the scenes is I'm probably going to
  2592. 3:19:32go and just give it a bulletoint list of what it  needs to do. Like basically if you think about it
  2593. 3:19:37um it needs to interpret my request. it needs to  convert that into an input friendly JSON object
  2594. 3:19:49using um you know like a location table UTC.  Then it needs to send the request to um some
  2595. 3:19:58big long URL which is going to look something  like this just with a different appy token.
  2596. 3:20:03And then it needs to return to user alongside  CSV etc. I also think I might just simplify
  2597. 3:20:13the number of steps so that all we're doing is  the appy search extraction then any mail finder
  2598. 3:20:16enrichment for now. Um so I'm going to do that  next. Just heading back over here. Just going to
  2599. 3:20:22paste all this in. I'll say let's adjust the logic  to the following. Okay. So I ended up running out
  2600. 3:20:28of tokens halfway through this build. Let me just  show you guys what that looks like and then how
  2601. 3:20:31you can solve it. So, basically, if you use Gemini  3.1 Pro, that obviously being the most in demand
  2602. 3:20:36model right now, given the fact that it's, you  know, new, really good at UX and stuff like that,
  2603. 3:20:40eventually you will probably run into some rate  limits. This case, this rate limit occurred after
  2604. 3:20:44about an hour of this working independently on its  own to solve some problem with some rate limit.
  2605. 3:20:48I just went and I walked away and then I came  back and then I saw that um sorry, with the uh
  2606. 3:20:53with the app scraper. And so essentially how you  proceed from here, at least my recommendation is I
  2607. 3:20:58would use a different model using the agent chat  UX. So I went down to claude opus 4.6. And then
  2608. 3:21:05I said first generate a comprehensive prompt that  includes everything that we've talked about so far
  2609. 3:21:09so I can paste it into another version of CC. CC  being cla. I'm now going to copy this. Okay. Then
  2610. 3:21:16what I'm going to do is I'm going to open this  up in claude code. And not only am I going to
  2611. 3:21:21open this up in cloud code, I'm also going to do  something called fast mode because claude has an
  2612. 3:21:25additional piece of functionality that uh Gemini  does not currently possess. That is the ability
  2613. 3:21:29to go very very quickly. I'm then going to double  check my extra usage. Looks like I'm 600 bucks in.
  2614. 3:21:36So I'm just going to go extra- usage. Keep in  mind you guys aren't going to be spending $600
  2615. 3:21:40and stuff on cloud code usage. Why don't I just  change this to 700? Um I just use a I use this for
  2616. 3:21:45like so many different things, right? juggling  five or 10 projects simultaneously. So for me,
  2617. 3:21:50700 bucks in additional usage might be I don't  know an additional 20 or 30 bucks per project.
  2618. 3:21:56Then I'm going to set that monthly spend limit.  Going to give that a little refresh here. Now
  2619. 3:22:01it's up to 86% use. So I have 14%. Okay. And then  I'm just going to exit out of this and then go
  2620. 3:22:06to a new one. I'm just going to paste all this in  now. I'll say proceed. And now there will be this
  2621. 3:22:14little lightning icon down here which denotes that  it's in fast mode. And then I get to make use of
  2622. 3:22:18um you know claude code or claude opus 4.6  thinking I should say on fast mode while I wait
  2623. 3:22:23for my Gemini usage limits to come back. Now you  don't have to do this. If you don't want to you
  2624. 3:22:28know juggle multiple models like I'm doing right  now. If you're happy to trade a little bit of time
  2625. 3:22:32for speed then by all means absolutely go ahead  and just use like the claw opus 4.6 built into um
  2626. 3:22:38the Gemini or agent chat inside of anti-gravity.  In my case, I want this to work as quickly as
  2627. 3:22:43possible since on kind of a time crunch here. I'm  going skating with my girlfriend. So, we're going
  2628. 3:22:48to see how much of this we could do in 15 minutes  just using the fast mode. And I'm happy to make
  2629. 3:22:52that time money trade um as necessary. What you'll  see about Claude is it's just significantly I want
  2630. 3:22:59to say more verbose with its notifications and  the information and it's also a lot easier to
  2631. 3:23:04follow along. That's one of the downsides of the  Gemini series of models, just like a little less
  2632. 3:23:08interpretable. Um, the thinking tabs and stuff  like that here are basically just in natural
  2633. 3:23:12language and I can follow along with them almost  as if it's me doing the thinking. Uh, which is
  2634. 3:23:17one thing I appreciate. Obviously, you do have to  weigh each of these minor pros and cons against
  2635. 3:23:22uh, you know, the model's ability to do things  like do front-end UX is really pretty and and so
  2636. 3:23:26on and so forth. Cool. So, this looks pretty solid  to me. We now have the server. It's going to test
  2637. 3:23:32the API endpoint directly and it looks like we  have some internal server error. It's now just
  2638. 3:23:36going to go through and then update model ids and  make minor terminations um as to what the error is
  2639. 3:23:41until we're we're good to go. And it's telling  me that it is currently running an appy actor
  2640. 3:23:46run. So I'm going to take a peek at this right  here. Looks like we ended up finding five leads,
  2641. 3:23:51which I think was initially what we asked for.  Going to head over scrape here and I'll say HVAC
  2642. 3:23:55owners in Texas. Let's do 100 leads. We'll run  the workflow. Looks like we've now generated the
  2643. 3:24:00filters right down below. So, it's now scraping  leads with this poll. And um this is just for I
  2644. 3:24:05guess our own our own purposes essentially. You  know, if we ever want to modify what the target
  2645. 3:24:09audience is or our job name, we can do so just  by maybe being a little bit more descriptive or
  2646. 3:24:14maybe being a little less descriptive. Okay,  we've now completed the job. We have the CSV
  2647. 3:24:18over here and I can actually open it and you  can see all these leads are now scraped. So,
  2648. 3:24:22we were basically like 99% of the way there right  before I ran out of tokens. Just needed uh another
  2649. 3:24:26model to get it over the line. This looks great.  Now let's re add the personalization workflow.
  2650. 3:24:34Use claude sonnet 4.6 as well. Okay. Now I'm going  to do the exact same thing. HVAC owners in Texas.
  2651. 3:24:42We're going to test the lead scraping. We can also  test the AI personalization as well. I'm doing 100
  2652. 3:24:46leads. So this should occur reasonably quickly.  Should be another five or 6 seconds. Okay,
  2653. 3:24:51looks like we're done with that. Now we're  doing AI personalization. So Claude in this
  2654. 3:24:54case is generating personalized ice breakers  for all of the leads that are in our database.
  2655. 3:24:58Something I'm noticing here is the AI  personalization is taking more than five
  2656. 3:25:02or 10 seconds. I imagine this is probably because  we're passing 100 rows sequentially or serially.
  2657. 3:25:06If you think about it realistically, you don't  need to do that sequentially or serially. You
  2658. 3:25:09could do that parallel in a parallel and send 100  requests simultaneously, whatever the the rate
  2659. 3:25:14limits are. So, I'm going to ask it to do that.  I'll say batch the requests. Make do whatever
  2660. 3:25:19you have to do to make it faster. Okay. I'm then  going to rerun this. We'll go I don't know HVAC
  2661. 3:25:25owners in Canada instead of Texas. Let's just  make sure that lead generation uh filter thing
  2662. 3:25:31still works. So, this is now Canada. We still  have a bunch of size filters down here as well,
  2663. 3:25:34which is cool. Because I'm only doing 20, this  should occur significantly faster. We're now
  2664. 3:25:39moving on to the AI personalization step. And  then at the end, we're now at completion and
  2665. 3:25:43export. That looks great. We're going to download  the CSV. Just going to open this up again. Make
  2666. 3:25:47sure we have that personalization column. Where  is that personalization column? Here we go.
  2667. 3:25:53Hey, Jean Michelle. Revolutionizing luxury best in  77 is no small thing. Bane Ultra's legacy speaks
  2668. 3:25:59for itself. Wanted to run something by you. So,  I'm not really liking how this is looking. It's
  2669. 3:26:02just a little too much right now. So, I'm going  to want to make this significantly more casual
  2670. 3:26:05and cleaner. I'll head back to configuration.  Okay, these are looking a little better. Still
  2671. 3:26:10probably not the best personalizations we could  be doing, but I think just for the purposes of
  2672. 3:26:13demonstration, I'll leave it there. Hey Kate, love  what you're building at Posh, also in engineering
  2673. 3:26:17services. Wanted to run something by you. I  can see that work reasonably well as an email
  2674. 3:26:20icebreaker. So, let's just exit out of this. We'll  close this older one. And uh from here on out,
  2675. 3:26:25all we really need to do, if you think about it,  is we need to fix this UX problem. Um we need to
  2676. 3:26:31add authentication with Superbase. And then we  need to take this puppy live. So I'm just going to
  2677. 3:26:35do a big voice dump here and get it to the point  where the quality is significantly improved. I'm
  2678. 3:26:39going to do that as taking a screenshot of this  section. And then coming back to Claude, we'll
  2679. 3:26:45paste this in. Then I'll say, "Hey, the current  app looks great. There's just a few issues.
  2680. 3:26:52The order history page looks really squashed and  not at all like the rest of the pages. I want it
  2681. 3:26:57in that nice clean style um similar to the scrape  page and the configuration page. We also need to
  2682. 3:27:06put this live and uh get this on superbase. So  I'm going to set up a superbase instance and I'd
  2683. 3:27:12like you to assist me in the connection of that.  We need all of the fields of relevance including
  2684. 3:27:20um database fields for the configuration, the  prompt engineering, API integrations, basically
  2685. 3:27:25whatever you've done locally just applied to um  you know a database instead. Last but not least,
  2686. 3:27:32when you click on an order in order history,  it opens up this nice side modal, but it's
  2687. 3:27:37not very tall at all. I want it stretched out to  contain such that I don't have to scroll through
  2688. 3:27:44um the div containing all of the information. If  that's unclear, just let me know and I'll clarify.
  2689. 3:27:51I'm going to dump this in and then I'm also going  to just because I'm using a new instance of cloud
  2690. 3:27:56code here. Just going to go back and then I'm  going to copy all of this. And I'm doing that
  2691. 3:28:03because I want to give it context, but I also  don't want it to like go ahead and redo stuff on
  2692. 3:28:06the app ify scrape and so on and so forth. While  that's occurring, I'll head over to Superbase.
  2693. 3:28:10And then we'll click start your project. I already  do have a couple of apps set up. I think what I'm
  2694. 3:28:15probably going to do is just delete one of these.  H probably delete the proposal generator app and
  2695. 3:28:22then set up a new one just because I think you're  only allowed two on a free plan. And um I want to
  2696. 3:28:26show you guys how easy it is to set all the stuff  up. So just going to delete that. And then I'll
  2697. 3:28:30go new. I'm going to call this one um let's go  Nick J Wellsorg. We're going to call this leadso
  2698. 3:28:38DB. I'm just going to do a strong password  automatically here. Copy that. And then I'll
  2699. 3:28:43enable the data API. Click create new project.  I'm just going to give it all the information
  2700. 3:28:48that uh it needs in order to set up this database  just like I did last time. Okay. So, first thing
  2701. 3:28:54is head back to anti-gravity. I'm just going  to paste this in. That's my DB password. Then
  2702. 3:29:01I'll head over to this left hand side here where  it says project settings. I'll go project name
  2703. 3:29:11and then we'll also go project ID.
  2704. 3:29:17I think there's one more. We just  need the API key so we could do a
  2705. 3:29:20lot of that work for us. So we'll go secret key.
  2706. 3:29:28And then we'll also go superbase public key.  We'll copy that as well. And this should have
  2707. 3:29:35everything that we need. I think what it's  going to do now is probably just set up O for
  2708. 3:29:39us. So head over to authentication where it says  email. And this time I don't actually want it to
  2709. 3:29:44confirm the signup. So I'm just going to go back  to emails and then where I click on sign on signin
  2710. 3:29:50providers. I'll just turn off confirm email. That  way I can make an account without having to do
  2711. 3:29:54that back and forth. Great. set up superbase and  off. I'll give a bunch of information here. So,
  2712. 3:30:02I think this is probably everything that it  needs and then we're just going to head over to
  2713. 3:30:06um SQL editor where it's going to give us  a bunch of SQL for us to paste in. Now,
  2714. 3:30:10my Gemini usage limit resets just in a few  minutes here. Um just because I have all of
  2715. 3:30:14the context inside of Cloud Code and it's going  through and doing this work, I'm probably just
  2716. 3:30:18going to continue in this Cloud Code thread  at least until I'm done this migration.
  2717. 3:30:22um then I can start up another agent chat  uh using you know anti-gravity's built-in
  2718. 3:30:26functionality and then have a conversation with  it. Uh in general you don't really want to jump
  2719. 3:30:30around between one model and the next unless you  can either fully export the conversation history
  2720. 3:30:34or you could do some sort of midway summary like  I just did a moment ago um from the anti-gravity
  2721. 3:30:38to claude or sorry from the agent chat to Claude  code direction. If I were to go the other way,
  2722. 3:30:44I'd do the exact opposite. I asked Claude to give  me a detailed project description of everything
  2723. 3:30:48that is currently occurring and all of its current  context. So I could immediately just segue that
  2724. 3:30:52into um the the conversation with Gemini 3.1 Pro  high. Okay, it's given us a plan and I've already
  2725. 3:30:58enabled this plan and let it go. So we have the  superbase URL, the anon key, service ro key and
  2726. 3:31:03and so on and so forth as well as a bunch of  other information here. It's going to start
  2727. 3:31:08with the environment variables, give me an SQL  migration file, do some client updating, add a
  2728. 3:31:13bunch of protected routes using authentication  middleware, finish the login and signup pages,
  2729. 3:31:17have a log out function as well, set up the config  page, do the orders page, do the scrape page, um,
  2730. 3:31:23set up the API layer, and then connect that to  Netlifi functions before finally building and
  2731. 3:31:28verifying. There's going to be some back and forth  there for sure. Um, but just like we did this with
  2732. 3:31:32Gemini 3.1 Pro High, we'll do the same thing  here. So, I have the migration right over here.
  2733. 3:31:36I'm just going to copy all of this in. And then  we're just going to remove these little comments.
  2734. 3:31:47And then what I'm going to do is just click  run. This will go through and then set up
  2735. 3:31:51our database. You can now see this in database  because we have a scrape jobs table with all of
  2736. 3:31:56these fields. The user configs table with all  of these fields as well. Any mailfinder key,
  2737. 3:32:00system prompt, instantly key, and so on and so  forth. And these are all going to be um sort of
  2738. 3:32:04fed into this authenticated user. So this is what  the authenticated user will sort of have access to
  2739. 3:32:09when they go from one route to the next. At the  same time, it's going through and then updating
  2740. 3:32:13everything that it's set up to do locally using um  JSON and JSL files to work through, you know, API
  2741. 3:32:19requests to the Superbase PostgresQL server to the  Superbase Postgrql database. And this is actually
  2742. 3:32:25a really good use case of using two different  models. The first is to build and the second is
  2743. 3:32:30to basically spot check what the first model did  without full context. The reason why is because
  2744. 3:32:34when you don't have the full context, your uh  opinions aren't really like polluted by the fact
  2745. 3:32:38that you're the one that spent all this time and  energy working on it. Just like you always have
  2746. 3:32:42like empirical or peer reviewers in papers and  and studies and research and stuff like that. So
  2747. 3:32:47too do I recommend doing this with models as well.  Having an unbiased third party review our code is
  2748. 3:32:52what is ultimately going to make our code and our  app significantly higher quality. Funny how models
  2749. 3:32:57are kind of like people in that way. We could  theoretically go back and forth and back and forth
  2750. 3:33:01with Claude Opus 4.6 designing something, Gemini  3.1 Pro High designing something else. Um, but I
  2751. 3:33:07think just one of these passes is good enough. And  in a way, that's what we're already doing with our
  2752. 3:33:11security audit if you think about it. Okay, it's  asking me to run the migration. I already did. So,
  2753. 3:33:14I'm saying done. Let's test it. It's now going to  launch this live. And imagine there'll probably be
  2754. 3:33:19some back and forth just like there was before.  Why don't we click get started? I'll say nick
  2755. 3:33:23sarif nick atniki.com and then we'll go I don't  know nikki nikki. Click sign up. Okay, we are
  2756. 3:33:32now being automatically taken to that config page  just like I wanted to. So here is where we'd set
  2757. 3:33:36up our keys and then we have that prompt which is  automatically set up. That's kind of cool. Okay,
  2758. 3:33:41I think what we need to do is we actually need to  modify this prompt to make sure it it's actually
  2759. 3:33:44like being reflected in the end result. Um and  then obviously we need a way to stick our tokens
  2760. 3:33:49in there. So, what I'm going to do for now is I'm  just going to go grab the ENV file here. I already
  2761. 3:33:55have my token. So, I'm going to copy this. I'll go  this API. Okay. Paste that in. Annie Mailfinder,
  2762. 3:34:01we'll paste that in. Enthropic. We will paste  that in. Okay. Now, I want to save changes.
  2763. 3:34:08Just reflect that this actually works. So, it  says saved. If I refresh this, I'm seeing that
  2764. 3:34:13the state is the same, which is good. If I make  a spelling mistake here and save, I'm seeing that
  2765. 3:34:18the changes are reflecting here as well, which  is good. I go to orders, there's nothing. Okay.
  2766. 3:34:23If I go to scrape leads now and I say, find me  a bunch of HVAC companies in Canada, owners of
  2767. 3:34:29HVAC companies in Canada, and I go 20 leads, and  I run this workflow, is this going to work? So,
  2768. 3:34:34it's gone through and it's generated the filters.  Let's just see what it's saying here. It's now
  2769. 3:34:39scraping the leads. Now, we're doing some AI  personalization. And I'm just playing around the
  2770. 3:34:43UX here. This is nice. This is nice. and smooth.  I like this a lot. I also like these cute little
  2771. 3:34:48animations and whatnot that it's decided to put  in. Okay, job completed successfully. I also like
  2772. 3:34:52how on the lefth hand side it's renewed. I don't  like how this little um scroll wheel animation on
  2773. 3:34:57completion and export continues. So, I'm just  going to head back, turn off the scroll wheel
  2774. 3:35:01animation on completed when the job is scraped.  When the job scrape is complete, completion.
  2775. 3:35:13Okay, that'll be good. But for now, let's actually  download the CSV. We got our leads up here. Just
  2776. 3:35:18going to take a peek at them. Same thing I did  before. Okay, icebreaker is looking great. Love
  2777. 3:35:22what Proparts doing in modular construction. Also  work in the space. Love the tutor teach model.
  2778. 3:35:25Connecting educator students is no small fee.  That's reasonable. So this clearly inherited our
  2779. 3:35:29good um result. Then finally, if I go to orders,  we can see this is now populating our database
  2780. 3:35:34successfully. What happens if I click? Awesome.  We have all of the data. Looks really clean. We
  2781. 3:35:38have the parsed filters. We have the profile  scrape. You can actually download the verified
  2782. 3:35:41CSV here as well. That's clean. Very nice. Okay,  the last thing I'd say is this three. These three
  2783. 3:35:47dots don't do anything. Also, the three dots to  the right hand side of an order in order history
  2784. 3:35:56do nothing right now. Okay, that's clean. And  then if I go down here to log out. Okay. Well,
  2785. 3:36:05let's just quadruple check everything else  is good. Looks like it. We're back here.
  2786. 3:36:13I think it was nikki.com, right? Yeah.  Okay, cool. Awesome. And I'm just going
  2787. 3:36:17to head back out and then test the rest  of my routes. So, if you guys remember,
  2788. 3:36:20there was scrape. Okay, that doesn't work. There  was config and there was also orders. Okay,
  2789. 3:36:25so all of the off middleware  here is working correctly. Um,
  2790. 3:36:28how's our landing page? It's looking pretty  clean. We don't have payment functionality yet,
  2791. 3:36:32which I'll cover in a second. This looks pretty  clean. If I click start, we go back. Nice.
  2792. 3:36:39Also, dress up the footer a little bit more. It's
  2793. 3:36:41quite small right now. That's on  the landing page specifically.
  2794. 3:36:47Okay, this is cool. I like that little like light  effect that we got in the background. Real clean.
  2795. 3:36:51Real clean. Um, product goes to product.  Pricing goes to pricing. Resources. Oh,
  2796. 3:36:56there is no resources link. So, we don't really  need that. Uh, I suppose we could probably make
  2797. 3:36:59a cute little logo. So, why don't we head over  to asstudio.google.com and just do that while we
  2798. 3:37:05can. I'm just going to see if I could link an API  key. Okay, I need a different account for that.
  2799. 3:37:10And over here, let's see if we can link a key.  And heading over here, let's see if we can link
  2800. 3:37:13a key. Cool. Generate me a simple square  logo, minimalistic, uh, straightforward,
  2801. 3:37:20but immediately interpretable and high-end for a  lead scraping SAS called Lezo. And then over here,
  2802. 3:37:26the aspect ratio is going to be 1 one. And we're  going to see if we can generate a 2K um, result. I
  2803. 3:37:32should also probably find some inspiration logos.  This looks pretty good just because it's simple,
  2804. 3:37:38straightforward, and obviously it's sort  of unique. If this gives me a bad result,
  2805. 3:37:42then I'll say something along the lines of that.  No, sorry. Flat icon style. Look at the below for
  2806. 3:37:49inspiration. Mimic this. Okay. And then going  back to our landing page at the very bottom,
  2807. 3:37:53you can see we have significantly more context  including the logo, bunch of information down
  2808. 3:37:57here, and so on and so forth. I've also been told  that we should be good. Um, I just sign in here
  2809. 3:38:07on this little orders panel. This looks like it's  opening up something, but it's not showing up. So,
  2810. 3:38:12I'll just have to clarify a little bit more  what's going on. When I click the three dots,
  2811. 3:38:19it looks like the menu is being hidden within  the div. Then, if I go back to AS Studio,
  2812. 3:38:27we see we have this. This isn't bad, to be honest.  Great. Remove the text. Let's just keep the shape.
  2813. 3:38:32Okay. And I don't know if you guys could see  this, but at the very top right hand corner, we
  2814. 3:38:35now have our little custom logo put in. Um I mean  like I think this could probably be a little bit
  2815. 3:38:40bigger. So why don't we make the background color  a little lighter gray? Looks good. Why don't we
  2816. 3:38:44make the background color a little lighter gray?  Okay. And then if I go to get started, you can
  2817. 3:38:49see that we now have that little new Leadzo logo.  And the colors here match the uh sign up button.
  2818. 3:38:54So I mean, is this going to win any awards for  its design? Yes, of course. It's it's gorgeous.
  2819. 3:38:59No. Uh, jokes aside, you know, maybe I had a real  logo designer come in here or maybe I iterated a
  2820. 3:39:03little bit more on the logo, we'd have something  that looks a little bit better. But the rest of
  2821. 3:39:06it looks real clean. I mean, if I don't know, this  was an Nvidia logo or something. I probably think
  2822. 3:39:10this is like an Nvidia style interface. It's  wonderful. Um, so looks great. Let's launch
  2823. 3:39:15this thing. Now, because we've done a fair amount  of work on Netlefi already, we had to use Netlefi
  2824. 3:39:20to like do the backend functions or whatever. That  was the design um pattern that the agent decided
  2825. 3:39:26on. This is already on Netlefi. All we really have  to do is just change the URL and then create the
  2826. 3:39:31site itself. Just jumping into Netlefi here. There  is now a leadso project created a few seconds ago.
  2827. 3:39:36Um that is manually deploying. I don't want it to  manually deploy. I just want to show you guys how
  2828. 3:39:40you can link it with GitHub. So I'm just going  to pause this and say set up GitHub as well and
  2829. 3:39:44then link the two. And so this now apparently is  online. If we go here we have leadzo.netifi.app.
  2830. 3:39:52So this is actually on like a real URL. So we  could see up top. Um, I think this might have
  2831. 3:39:56made the uh logo a little bit brighter than I  was initially anticipating, which is cool. But
  2832. 3:40:00remember that I want this to be um, you know, on  GitHub as well. So, that's what we're going to
  2833. 3:40:04do next. First, it's going to initialize the  Git repo. It may ask you to sign in if it's
  2834. 3:40:07the very first time you've done this before.  I've done this many times before. So, my um,
  2835. 3:40:11anti-gravity instance is basically already linked  to my specific GitHub account. It's now going to
  2836. 3:40:15do what's called git ignore, which is take a bunch  of these files that probably shouldn't be pushed,
  2837. 3:40:19like all of my API keys, then ensure that those  don't actually go live. Now it's creating the
  2838. 3:40:24actual thing and then linking it to Netlify. It'll  handle whatever errors it has in its own syntax
  2839. 3:40:29mostly autonomously. Just checking for mobile  optimization as well by making my browser window a
  2840. 3:40:34little smaller and then dragging it all the way to  the left. This looks pretty clean to me. I don't
  2841. 3:40:37see any major issues. Nothing so far. Nice. Cool.  All of these are arranged the way they should
  2842. 3:40:44be. Pricing. Excellent. Okay. Get started today.  Beautiful. Now, how about the actual login page?
  2843. 3:40:52Yep, that looks good. Then how about Nikki? Nikki  is the password. Okay, so the actual app page not
  2844. 3:40:59super mobile optimized. Everything else is. So  what I'm think I'm going to do, which is my final
  2845. 3:41:03command essentially, is excellent. The landing  page and a sign-in pages look great, but the um
  2846. 3:41:11dashboard stuff after you sign in is not optimized  for mobile. Make sure that it works on mobile
  2847. 3:41:17displays as well. And while all that stuff's  going on, I'm also going to do our security audit.
  2848. 3:41:20What's cool is I could do a lot of these things  in parallel side by side. So whereas previously
  2849. 3:41:25I had Cloud Code do the security audit, I'm not  just going to paste this big security prompt into
  2850. 3:41:28Gemini 3.1 Pro High for a couple of reasons. One,  I've already used like $800 of my Cloud Code limit
  2851. 3:41:34at this point and I don't want to spend anymore.  Um, another is that the Gemini model uh rate limit
  2852. 3:41:38runs out at a specific time and then like it's  usually back within an hour or so. I think they
  2853. 3:41:42do it like every 2 hours or 3 hours or something.  So yeah, I just uh Oh, and the third is I just
  2854. 3:41:47want to test how it is compared to the Cloud Code  experience. So, we're going to allow this whole
  2855. 3:41:51conversation here and then it's just going to  run through top to bottom and do that security
  2856. 3:41:54audit. Um, what's cool is now we're pushed to  GitHub, right? Because we're pushed to GitHub,
  2857. 3:41:59we can actually do a lot more of the um kind of  like uh version control based security things that
  2858. 3:42:04we couldn't do that last time because it was more  of like a because we had just dragged and dropped
  2859. 3:42:07the folder directly into NFI. So, it looks like  it's doing pretty well mapping out the front end
  2860. 3:42:12and backend LFI functions entry points, checking  ignore for secret management. I'm just going to
  2861. 3:42:16let this go on its own and then uh along with the  designed components and stuff like that, we can
  2862. 3:42:21get to that um when it's all done. Heading back  to the app, which is now online, I'm actually just
  2863. 3:42:27going to do one final mobile optimization check.  So, that looks really nice and solid. I'm now
  2864. 3:42:32going to sign in. We'll go nickniki.com. And then  I think the password was like Nikki Nikki. Um this
  2865. 3:42:40new scrape job here is looking really clean. As  you can see, we actually have that functionality.
  2866. 3:42:44Let me just move my head. We actually have that  functionality now where all of it is contained
  2867. 3:42:48within like a mobile browser um view which is  really cool. And then we also have that little
  2868. 3:42:54navbar. So I'm going to head to orders. Orders you  know it's going to be a little tougher by nature
  2869. 3:42:58I think but uh included this little horizontal  scroll wheel. And so I'm still technically going
  2870. 3:43:03to call that mobile optimized. I guess we could  just like redo the whole structure and have job
  2871. 3:43:07ID here, target request here, profile scraped  here, but it'd be a little bit annoying to do
  2872. 3:43:11that. And I kind of like having a table. Tabular  data is um notoriously different to turn into like
  2873. 3:43:16mobile optimized form when you're working with  tables and HTML. So I think I'll just leave that
  2874. 3:43:21there. This page looks really clean. I really have  no issues. Um I'm I'm honestly quite pleased with
  2875. 3:43:26the performance of Gemini and Claude Code together  on this app. So 10 out of 10 would do again. Um,
  2876. 3:43:32we do have one more feature I guess which is that  feature that I talked about earlier where um,
  2877. 3:43:37you know, if it doesn't scrape the leads through  Appify, uh, sorry, the Appify codec crafter actor,
  2878. 3:43:43then I wanted to pass that off to Google Maps.  Uh, I think for the purposes of demonstration,
  2879. 3:43:48like we're pretty close to just wrapping up the  app. And the purpose of this was not to do like
  2880. 3:43:51some super crazy endto-end uh, like 500 different  platform scraping flow. The purpose is to show you
  2881. 3:43:56guys how to wrap around an API and how simple that  is. So, I think I'll probably just leave that as
  2882. 3:44:00that actor for now. But uh rest assured you could  very quickly and easily weave in uh you know logic
  2883. 3:44:05like hey if this thing returns zero leads then I  want you to use this other approach. Um yeah that
  2884. 3:44:11looks pretty good to me. I guess we could also add  that post any mailfinder step. H I might just do
  2885. 3:44:17that instead once we're done the security audit.  Um generally speaking though you do want to do
  2886. 3:44:22the security audits at the very end. So might be  skipping a step here. Not that big of a deal. Just
  2887. 3:44:26wanted to make sure we're all on the same page.  On the security side, if I just open up this agent
  2888. 3:44:29window, you can see that it has actually found  some major issues. Found major off bypass in the
  2889. 3:44:33API routes. It also found a hallucinated enthropic  package dependency. So, it's preparing some final
  2890. 3:44:38checks. That is a big deal, right? Um, you know,  it's done more or less exactly what I've asked it
  2891. 3:44:44to do. Go through with a fine tooththed comb and  see whether or not we can access routes without
  2892. 3:44:49actually having any sort of credentials. I can  open up the task right over here. And, uh, this is
  2893. 3:44:53where we're at. The first phase was where it was  just identifying and running through the codebase.
  2894. 3:44:58And the second is now where it's running through  every single step here sort of like a tabular way.
  2895. 3:45:03It's now finishing up the report generation.  We're going to take a look. So this looks like
  2896. 3:45:08it's quite critical. We have authentication bypass  and paid API routes, some hallucinated malicious
  2897. 3:45:13package dependencies, missing with check clauses  and so on and so forth. So, what we can do is we
  2898. 3:45:18can actually go through this whole thing and  not have this hallucinated anthropic package,
  2899. 3:45:23but instead use the atanthropic-ai- SDK. So, I  think what I'm going to do is we're probably just
  2900. 3:45:30going to push it. Okay, great. Do the security  fixes, make sure the app still works, of course.
  2901. 3:45:39And now we're going to run through this big list  of detailed findings and fix it. Of note, this is
  2902. 3:45:43significantly less secure than u the other app.  just off the get-go. And it's probably because
  2903. 3:45:48we have some additional functionality where  we're basically like piping through API requests
  2904. 3:45:52and whatnot, right? We're also using a slightly  different framework. We're using Vit instead of
  2905. 3:45:56Nex.js, which I think solves a few of these. Um,  in total, I think the score is like something like
  2906. 3:46:0170% or so, whereas the previous app, I think,  was a little bit higher. But yeah, you know,
  2907. 3:46:05some of these are quite quite severe. The fact  that you could bypass um the authenticated user.
  2908. 3:46:10So if they're not authenticated, it skips the  check entirely and proceeds to use the fallback
  2909. 3:46:14process API keys to execute the scrape. Any  visitor can hit this endpoint via curl or postman
  2910. 3:46:19without authenticating and your server will gladly  run expensive API ampy jobs, open a analysis or
  2911. 3:46:23anthropic calls all build to my personal account.  This is the same sort of issue that um I think
  2912. 3:46:28there was with OpenClaw at the time where um  you know you could just like bypass one of
  2913. 3:46:32the routes entirely, go on like their dashboard  and then if they had some little server bypass
  2914. 3:46:38uh setting or flag not like explicitly opted out  of then you could actually just use their own
  2915. 3:46:42keys. And so in this way a lot of people had their  keys used not only leaked but also used and run
  2916. 3:46:46up something like 25,000 people. It's yeah quite  a big deal. Looks like we're now installing some
  2917. 3:46:51input validation libraries and stuff like that  and it's fixing the bypass. I'll get back to you
  2918. 3:46:55guys when all this stuff is done. Excellent.  Looks solid. We now have everything that we
  2919. 3:46:59need. I'm just going to take a quick peek at the  final version of the app. Make sure everything
  2920. 3:47:03here works the same way that it did initially.  Opening up another list here. And this looks
  2921. 3:47:07solid. Excellent. So hopefully you guys now see  how you guys could use Gemini in conjunction with
  2922. 3:47:13cloud code and anti-gravity to build an app not  only that has full stack database authentication,
  2923. 3:47:18everything else, but that also wraps around like a  pre-existing API. As mentioned, a lot of fantastic
  2924. 3:47:23um SAS apps nowadays will either incorporate a  wrapped API as like their main functionality or
  2925. 3:47:28they'll like include this as one of the five  or 10 or 15 different things. Realistically,
  2926. 3:47:32like the software is no longer the moat. It's not  really that like, you know, you're going to build
  2927. 3:47:36something super incredible that solves a problem  that nobody else has ever solved before and then
  2928. 3:47:41you're going to package it in a beautiful UX that  nobody has ever put together before and then, you
  2929. 3:47:45know, put it on the internet and then that is what  is going to distinguish you out from from somebody
  2930. 3:47:49else. And so in this way, you know, there are a  lot of short-term opportunities you could take
  2931. 3:47:52advantage of through app creation just by wrapping  pre-existing APIs that already do most of the
  2932. 3:47:57heavy lifting for you. And hopefully this Appify  example um was was a a good show of what that
  2933. 3:48:02might look like. And by the way, just so we're on  the same page here, this is just one tiny little
  2934. 3:48:06actor of like thousands of different scrapers that  you could use. Just scrolling through Appify here,
  2935. 3:48:11you guys see there's stuff like uh Trip Advisor  review scraper, DraftKings Scraper, there's
  2936. 3:48:15Instagram scraper, website content crawler,  tweet scrapers off Twitter, land.com search,
  2937. 3:48:20Instagram comment bots, and so on and so on and so  forth. You could build whatever functionality you
  2938. 3:48:24want just by wrapping them around this service,  which is quite affordable um and you know,
  2939. 3:48:29straightforward and easy to use. And there also  a bunch of other services out there that are like
  2940. 3:48:33this that do um similar things. So, I'm not going  to tell you how to use one service or another,
  2941. 3:48:37but yeah, like this Appify or API wrapper game  is super super powerful and it's blowing up right
  2942. 3:48:43now. The one thing that we didn't build today,  obviously, was the payments integration, which is
  2943. 3:48:47sort of like that final missing piece. Um, so I'm  going to talk a little bit about payments now and
  2944. 3:48:50then after I'm done talking about payments, we'll  actually go through and build our next app, which
  2945. 3:48:54is going to be one that allows us to go uh allows  users that use our app to go from everything from
  2946. 3:48:58like going on a landing page, clicking buy, buying  the product or service, having some tokens added
  2947. 3:49:03to their account, credits, and so on so forth,  going through like a full-fledged onboarding,
  2948. 3:49:07and then once the onboarding is done, basically  being able to use the app. And in this way,
  2949. 3:49:10we've successfully built up both our understanding  and then our capability from plain old websites to
  2950. 3:49:16um what will finally be like full stack apps that  combine everything that we've talked about here.
  2951. 3:49:20Okay, so let's have a brief conversation about  payments. We've obviously set up authentication.
  2952. 3:49:25We know what like the the general flow looks  like. When somebody signs up to your app, they
  2953. 3:49:28can either get some sort of email notification  that they can verify after they're done with
  2954. 3:49:31that. Then obviously they get they get access.  A lot of this is handled through authentication
  2955. 3:49:35middleware and routes and stuff. Um, but basically  in our case with payments, we're going to add one
  2956. 3:49:40final step. So, basically the user is going to  start by signing up, right? So, we already know
  2957. 3:49:44how to do this. It's pretty straightforward.  It's off. After they sign up, they're going
  2958. 3:49:47to be taken to their own private payment page  where they can pick a plan or buy credits. Now,
  2959. 3:49:52if you're doing like a thumbnail lead gener a  thumbnail generator app, for instance, obviously
  2960. 3:49:56it's probably going to be credit based. Um, if  you're doing something that maybe provisions
  2961. 3:50:00access to like a subscription service or something  where it's like, you know, you pay once and then
  2962. 3:50:03you do it monthly, then we'll probably do a plan.  um after the payment occurs, they'll get access,
  2963. 3:50:08which is referred to as entitlement. They'll  use the app, which is called consumption,
  2964. 3:50:12and then in some cases, like if you're using  credits, they may run out, in which case they go
  2965. 3:50:15back to the payment. That's sort of how it looks  under the hood. In terms of like what's going on,
  2966. 3:50:21um we're not going to do the payment processing  ourselves. Basically, everybody on planet Earth
  2967. 3:50:25now just uses pre-existing options like Stripe.  And the whole idea is when a user clicks subscribe
  2968. 3:50:29or buy credits or whatever um we just have an  agreement with Stripe where via API we redirect
  2969. 3:50:35them to a Stripeh hosted checkout page. Stripe  already has all the language and handles the card.
  2970. 3:50:39They do things like advanced fraud detection.  They do things like you know handle your tax
  2971. 3:50:43obligations like receipts and stuff like that and  then they just send all of that stuff to the user.
  2972. 3:50:48We never touch a credit card number. We just get  paid you know in return for doing this. Stripe or
  2973. 3:50:53these other payment processors they usually make  like a couple percentage points. I think Stripe
  2974. 3:50:56right now is 2.9 plus 30 cents per transaction  or something. Um, I'm very happy to pay the
  2975. 3:51:002.9 cents not to have to deal with this because  in addition to this being like a real cluster,
  2976. 3:51:05you know, don't want to swear too much on this,  but in addition to being a real pain in the ass,
  2977. 3:51:09uh, it is also kind of like a liability legally.  And, you know, as app developers, I want to
  2978. 3:51:13focus on building the app and marketing it and  stuff. That's what 99% of my work needs to be,
  2979. 3:51:17not handling the legalities. So when the payment  succeeds, and it will if you know the the card
  2980. 3:51:23is not fraudulent, if they cross their tees and  dot their eyes, Stripe will send our backend a
  2981. 3:51:29web hook, which is basically just like an event  notification that says, "Hey, this user paid,
  2982. 3:51:34this user that you've already signed up for."  So we have all their information and so so on
  2983. 3:51:38and so forth. Their ID um is good to go. Then your  backend will receive that. It'll update a field on
  2984. 3:51:43the user's record in your database. So in our case  our superbase that'll be something like plan is
  2985. 3:51:47now pro or credits are 50 and then your app knows  what it's allowed to do and then you know as it
  2986. 3:51:52uses and consumes those credits every single time  it'll basically make a request to the database
  2987. 3:51:55just reducing that a little. Um and then you know  because it's like this you can now do a variety of
  2988. 3:52:00of cool features. You could provision additional  app um credits or usage if you want. You have the
  2989. 3:52:06ability to like upgrade people, downgrade  people, moderate your app and everything.
  2990. 3:52:09So, three models are onetime purchase, which  is basically where you pay once, you get
  2991. 3:52:13access forever. It's really easy to do. You're  basically just selling a service, right? So,
  2992. 3:52:17you just flip a boolean on their account. Um, they  sign up via the Superbase O function. Now, they
  2993. 3:52:23have like a little like user table. Inside the  user table, there's a field that says subscribe,
  2994. 3:52:28question mark, and then it's either true or false.  In subscription, it's pay monthly and then the
  2995. 3:52:32access continues. Stripe has a bunch of features  inside of it that manage recurring subscriptions
  2996. 3:52:36or billing um on let's say a monthly or a weekly  or an annual basis. And basically what happens
  2997. 3:52:40is once you have the payment success or payment  failure um you'll receive a web hook and then
  2998. 3:52:45you just toggle that access and then Stripe will  manage that for you every single month. Basically
  2999. 3:52:49uh whenever a a successful payment comes in,  you'll keep it. If a payment failure comes in,
  3000. 3:52:53then you'll flip it. And then finally that  credit based usage where you basically just
  3001. 3:52:56buy a bucket of different um tokens or credits or  whatever the heck. every time they hit your API
  3002. 3:53:01to generate a thumbnail or scrape your leads,  you decrement the balance. When it hits zero,
  3003. 3:53:04you will send them back to checkout and then  force them to do it again. So, all of the apps
  3004. 3:53:07that we built in this course can use any of  these. Uh, if I was doing lead scraping, I
  3005. 3:53:10would probably do either like a monthly plan with  credits built in or I just do credits. Um, for
  3006. 3:53:15our thumbnail generator, we're just going to do  credits. But, you know, you you can use whatever
  3007. 3:53:19combination of these you want as well. The three  things we're going to need in our codebase,
  3008. 3:53:22and keep in mind like our models are going to  handle this for you. You don't have to do this,
  3009. 3:53:26but basically we need an endpoint that creates  a Stripe checkout session and then redirects the
  3010. 3:53:30user. So after the user signs up, they're going to  have to immediately go to this endpoint maybe with
  3011. 3:53:34three maybe a page with three different pricing  plans or something. Then when they click on that,
  3012. 3:53:38it'll redirect them over to Stripe with their  information. Then we need a web hook endpoint,
  3013. 3:53:43which is just like a little um route on our  server that basically waits to receive a payment
  3014. 3:53:49succeeded event from Stripe. Then it'll update our  database. And then finally, we need some way to
  3015. 3:53:53check inside of our app before doing the expensive  thing like generating a thumbnail or whatever,
  3016. 3:53:58does the user have valid uh plan? Do they have  valid credits? So that's exactly what we're
  3017. 3:54:02going to do in the next product build. You guys  are going to see this hands-on. I just want you
  3018. 3:54:06to know that basically this just stands between  like the authentication step, okay, and then the
  3019. 3:54:12um like usage step. Basically now there's just  going to be an additional one which is payment.
  3020. 3:54:18Before obviously I let people use their own API  tokens and stuff like that in the app. So we sort
  3021. 3:54:23of bypassed this alto together. Now it's going to  be you know like us doing the thing and therefore
  3022. 3:54:27we're going to want to make some arbitrage. You  know they're going to pay I don't know $10 and
  3023. 3:54:32then every usage is only going to cost us $1. And  so in that way we're going to basically make uh $9
  3024. 3:54:37in profit. That's more or less how any meaningful  SAS business will operate. Okay. So hopefully you
  3025. 3:54:41guys are as excited as I am. Let's dive into  it. So, in order to make any of this work,
  3026. 3:54:46you are going to have to go to stripe.com and set  up an account. Um, I want you guys to know that
  3027. 3:54:51if you don't have, you know, like an account on  Stripe set up, you're not really going to be able
  3028. 3:54:55to follow along with me. But, at the same time, I  know that depending on where you are in the world,
  3029. 3:55:00um, different people have different levels  of access to Stripe. They're not available
  3030. 3:55:03in every country. So, if you guys aren't capable  of using whatever, you know, the specific solution
  3031. 3:55:08I'm going to do, I recommend just use whatever  you guys have access to. Like, there's Payaneer,
  3032. 3:55:12uh, I don't know, there's like PayPal. While these  services are not as clean and as good as Stripe,
  3033. 3:55:16they don't handle as much of, you know, literally  global GDP at the moment. They're up to 1.6% which
  3034. 3:55:21is insanely bonkers. Uh they're still pretty solid  and, you know, there's a lot you can do with them.
  3035. 3:55:25Just trying to replace everything I'm about to  tell you with with that. So, you're going to
  3036. 3:55:28have to go through some prolonged signup process  obviously and some of the stuff is going to take
  3037. 3:55:32a while to implement. You're going to have to, you  know, verify your identity and stuff like any good
  3038. 3:55:35payment platform. Um, but this is really clean  and it's it's a really good service. After that,
  3039. 3:55:39you'll be taken to a dashboard that looks  something like this. in the top right hand
  3040. 3:55:42corner there'll there'll be a little test mode  toggle which I'd recommend turning on. If you
  3041. 3:55:46head to the top lefthand corner you can then go  switch sandbox and then click create sandbox.
  3042. 3:55:50That's what we're going to do. Um when you go  through that little prompt uh create it or model
  3043. 3:55:53it after you pre-existing Stripe account and then  you'll have an account that looks like this which
  3044. 3:55:57basically will just model over your real account  and then give you the ability to like collect
  3045. 3:56:02u publishable keys or secret keys at a  button. Make sure not to reveal these.
  3046. 3:56:06These are super important if you did reveal like  your your real keys, not your sandbox keys. Um,
  3047. 3:56:11a developer would basically have full access over  literally everything ever, which is kind of crazy.
  3048. 3:56:16So, don't ever do that unless you want a random  $10 million bill in your Stripe account. They'd
  3049. 3:56:21probably cap it after a few thousand, but yeah,  would not want that to happen to you. And then
  3050. 3:56:25once you're done with this, you're you're actually  pretty good. We're just going to give our agent
  3051. 3:56:27the publishable and secret keys, and then it'll  like handle the rest of the payments for us. Okay,
  3052. 3:56:31so that's step number one. Step number two, I'm  just going to go back to anti-gravity. And then
  3053. 3:56:34now, let's exit out of this lead scraping SAS. go  open folder and I'm going to call this thumbnail
  3054. 3:56:40generator. Open this puppy up. And now we are  basically in a fresh uninitialized workspace
  3055. 3:56:47here with just the folder name. And just like we  did the first couple of times uh to develop full
  3056. 3:56:52stack apps. We're going to do more or less the  same idea. I'm going to go find a screenshot of
  3057. 3:56:56something that I like that I think looks really  clean and that I want to model my app around.
  3058. 3:57:00And then I'm just going to like voice dictate  give it a big dump of what it is that I want it
  3059. 3:57:03to do. And then I'm just going to have it like go  and give me its demo. Um, once we have that demo,
  3060. 3:57:08we can like in that little mining gif, uh, or  sorry, mining meme, we can like progressively
  3061. 3:57:13mine all the BS until eventually we hit gold.  And once we've hit that little gold cavern,
  3062. 3:57:17then we can actually do some work and make our  app better and better. Um, at a very high level
  3063. 3:57:21though, uh, let me show you guys how I'm thinking  that this app is going to work. So, basically,
  3064. 3:57:26um, just like we had before, you know, we want  a landing page. That landing page is going to be
  3065. 3:57:31like any relatively simple marketing page, right?  What's going to occur is there'll be a little
  3066. 3:57:36payment section. When they click on this payment  uh button or whatever, basically what's going to
  3067. 3:57:41occur is they'll be taken to the authentication  or a sign up. Um after they sign up, they'll be
  3068. 3:57:46taken to the ability to pay and that'll be  like the one click that takes us to like the
  3069. 3:57:50Stripe checkout. We're going to do this based off  credits. So after they pay, we'll then provision
  3070. 3:57:55access to the app. What's the app actually going  to look like on the internal side? Um well,
  3071. 3:58:00it's going to be pretty straightforward. You're  going to have a dashboard which allows you to see
  3072. 3:58:03all of your generated apps, uh, sorry, generated  thumbnails and everything like that. You're
  3073. 3:58:07going to have like a config page similar to the  scraper that allows you to do things like upload
  3074. 3:58:12images of yourself. Um, when you upload images of  yourself, uh, you'll be able to basically have the
  3075. 3:58:16model generate thumbnails for YouTube or other uh,  content platforms that include you. Uh, and then
  3076. 3:58:22we're also going to have like the generate page.  And this generate page is where we're going to
  3077. 3:58:26be able to, you know, put in some some prompts  and and stuff like that. and then it'll pass
  3078. 3:58:30through. And the idea is what we're going to do  is we're going to pass through using nano banana.
  3079. 3:58:38And the way it's going to work is we're going to  feed in um like an inspiration thumbnail. And then
  3080. 3:58:46in addition, we're also going to feed in a prompt  with changes. And then it'll do its best to model
  3081. 3:58:52that. And it's not just going to do it once, it's  going to do it, I don't know, like three times.
  3082. 3:58:56And then it'll spit out, you know, three potential  options, A, B, or C. And then you just pick one.
  3083. 3:59:04And this is going to be the one that gets saved.  This is going to use our Nano Banana Pro key. And
  3084. 3:59:08so in that way, it's going to be consuming our app  credit usage. Um, we're not going to go through
  3085. 3:59:12the process of like signing up a developer app or  anything like that to to let that happen because
  3086. 3:59:17sometimes some of these platforms are like, hey,  if you want to resell our tokens or if you want
  3087. 3:59:20to resell credits, you need to go through  some additional steps. Um, but basically,
  3088. 3:59:23in a nutshell, that's going to be your completed  one. And then this is going to show up in orders.
  3089. 3:59:27And then every single time we do that, if you  think about it, we're also going to um consume
  3090. 3:59:31some credits that they have because they're  buying based off of credits. So I don't know,
  3091. 3:59:36maybe every time we generate we'll consume three  credits and then I don't know, maybe like it'll
  3092. 3:59:40be like $1 equals 10 credits or something. We'll  keep it really simple obviously, but if you were
  3093. 3:59:46a business, you'd actually want to run through  like the economics of pricing and stuff like that.
  3094. 3:59:50Okay, so pretty straightforward, pretty simple.  Um why don't we start with that first step which
  3095. 3:59:54is finding some design inspiration. Then I'm going  to do a big voice dump. After we're done with the
  3096. 3:59:57voice dump and the design inspiration, we're going  to produce it locally. Once we produce it locally,
  3097. 4:00:01we'll iterate test. Then we'll push it um to like  actual databases. We'll iterate test. Then we'll
  3098. 4:00:06make it live on Netlefi. Iterate test. Then  finally, we do a security audit. Same thing
  3099. 4:00:10that we did before. Just going to head over here  and I'll type web app because a lot of these are
  3100. 4:00:14mobile based and I just want this one to be  not mobile based for now. I want this to be
  3101. 4:00:19really clean. In fact, I want this to be like the  cleanest, sexiest app that we've developed so far.
  3102. 4:00:23So, I really like this design. That looks really  clean, but obviously it's not like a like an app,
  3103. 4:00:28per se. I also really like this design. Okay,  that's really sexy. I'm liking this like dark
  3104. 4:00:35kind of like glass. I don't know what it's called.  Isomorphism. Like, this is crazy. Activating new
  3105. 4:00:41brain paths. Look at how sexy that is. So,  we're going to go over something like that.
  3106. 4:00:45This one's really, really good. This guy Jack R is  a freaking genius here. He actually included the
  3107. 4:00:50font down below as well as the color palette and  everything like that. Um, this is for like some
  3108. 4:00:54app that supposedly monitors your brain waves,  which is wild. Uh, we're obviously not making
  3109. 4:00:59an app that monitors brain waves. We're making an  app that uh gets me more subscribers on YouTube,
  3110. 4:01:03but still super clean. I like this. And the fact  that he provided the fonts and stuff means that
  3111. 4:01:07I'm going for it. So, I'm just going to take this  image here, copy it, paste that into thumbnail
  3112. 4:01:13generator, and then I'm also going to feed in  just some design information. I'll say font lufka
  3113. 4:01:22um primary F4 E18E secondaries, and then I'll go  D6, D6, D5, and then D. Is that a B or an eight? I
  3114. 4:01:35think that's a B. DB DB DB. Uh, anything else that  we need? We also have the white is going to be E3
  3115. 4:01:44E3 E3 and then the black is going to be 043. Cool.  I'm just copying these over. I mean, obviously I
  3116. 4:01:50could just provide a screenshot, but I don't want  to consume that many tokens for what ultimately
  3117. 4:01:53amounts to just a few characters. Um, cool. This  looks really, really clean. I I like this. So,
  3118. 4:01:57we'll see how this goes. I mean, I don't know if  it'll be able to replicate the glass eomorphism,
  3119. 4:02:00but that's fine. Um, and then we'll close out  of these for now. Now that we're done with that,
  3120. 4:02:04I'm just going to give a big voice dump of more  or less everything I've already told you guys. So,
  3121. 4:02:07I'm not going to include this in the video so  you guys don't have to waste another few minutes
  3122. 4:02:10hearing me talk about it. But, I'm just going to  go back here, double click my voice transcription
  3123. 4:02:13tool, and then go for it. Hey, I'd like you to  help me build a full stack application. I will
  3124. 4:02:18provide you with all the relevant API keys down  here for now. Build this so it works locally using
  3125. 4:02:25JSON files as a standin for the DB. Later we'll do  the actual superbase etc setup. Cool. That looks
  3126. 4:02:35pretty good. Um quite the long prompt here. That's  one of the reasons why I really like these voice
  3127. 4:02:38dictation tools. You can just bang out, you know,  10 times the number of words. And what's cool
  3128. 4:02:44is models are pretty capable at extracting your  meaning. Better just to talk like you're talking
  3129. 4:02:50to a human being. Spit out whatever you can and  then the model will extract the important bits. So
  3130. 4:02:55that's more or less what I did over here. It's now  going through this. It's generating um you know,
  3131. 4:02:59a file structure using uh next.js, which  is what I asked it to use. Um and then,
  3132. 4:03:05you know, I'm going to give it all the API keys  and everything like that after it's scaffolded the
  3133. 4:03:09base structure. Okay. So, from here on out, we're  just going to sit around and wait for this thing
  3134. 4:03:12to do its magic. Awesome. So, it just wrapped up  and I now have this live on npm rundev. I then
  3135. 4:03:18navigate localhost 3000 and this is what it looks  like. So, this is unfortunately just calling it
  3136. 4:03:23nano banana. I think it probably misunderstood  what I was saying, but that's okay. No big deal.
  3137. 4:03:26Just going to refresh this here. See that we  have a bunch of the social proof pieces here.
  3138. 4:03:31Global tech nexus, Nebula, and so on and so  forth. Professional thumbnail. Zero Photoshop
  3139. 4:03:35skills required. That looks pretty clean,  honestly. Simple, pay grow. Pricing. I like
  3140. 4:03:39that. Ready to blow up your channel. Create your  first thumbnail. Okay, so let's see what happens
  3141. 4:03:43when I do get started. Takes us to this page.  I'll just say [email protected]. Continue with
  3142. 4:03:50email. Now we're being taken to a payment page.  This is really clean. I like this. Um hm. Going
  3143. 4:03:56to click pay $10 here. It's empty, but we should  still be good. And now we're on the thumbnail
  3144. 4:04:01uh generator side. So look at this generation  activity. Number of thumbnails generated per day.
  3145. 4:04:06No generations yet up here. Generate new will take  us to this page. And we actually have a pretty
  3146. 4:04:10clean UX. We have a generate magic inspiration  thumbnail. Generation prompt generated options
  3147. 4:04:141 2 3. These are what are going to generate.  We have the number of credit cost. We have a
  3148. 4:04:19settings page here with a reference face. We're  going to need multiple files. So I'm going to
  3149. 4:04:22have to make that adjustment. And then you guys  can't see this because my face is in the way,
  3150. 4:04:27but if I make this a little bit smaller, you see  how on the bottom left hand corner, we also have
  3151. 4:04:31a credits available with a top up button. This top  up button is going to bring us back to this little
  3152. 4:04:35payment page. Okay, so it's really clean, very  sexy, and pretty straightforward app. That said,
  3153. 4:04:40I don't like the design. The design is sort  of like a big issue for me. So, I'm going to
  3154. 4:04:45have it generate um a new design because I don't  like this. There are also some minor changes that
  3155. 4:04:49I think need to be made. Notice how the margin  on the left moves around every time. Obviously,
  3156. 4:04:54we have some minor UX changes as well, aside  from the design that I like to make. And uh yeah,
  3157. 4:04:59why don't we pick a name? Why don't we call it  Thumbly? I think this is actually the the name
  3158. 4:05:03of one of my startups now that I'm mentioning  it. It used to literally be called Thumbly,
  3159. 4:05:07and it was something similar. I was like creating  uh thumbnails for people. Oh yeah, look at that.
  3160. 4:05:11That's wild, man. I made this thing like probably  five, six years ago. That's a friend of mine,
  3161. 4:05:15Zach, that since worked with Scaling with Systems  and a bunch of other people. Anyway, super clean,
  3162. 4:05:20huh? Not gonna lie. Okay. Okay. This is how  it works. You basically basically generate
  3163. 4:05:25thumbnails and then you can select them. Man, I  coded this by hand back in the day. Uh, okay. So,
  3164. 4:05:29let's call this thumbly. And then let's also  make a bunch of changes. I'm just going to do
  3165. 4:05:34some voice dictation. And then I'm also going to  like have it really push for that high-end white
  3166. 4:05:38design style cuz I don't like this first demo. So,  I'm going to say let's call it thumbly feedback.
  3167. 4:05:45And now I'm going to give it a bunch. The design  needs to be heavily modified. It does not reflect
  3168. 4:05:52the provided image at all, unfortunately. On the  overview page, I'd like you to remove the average
  3169. 4:05:58CTR impact section and then replace it with  something else that we would realistically have
  3170. 4:06:03access to. The generation graph looks cool. When  I go between overview, generate, and settings,
  3171. 4:06:09I'm noticing that the left hand margin of the  generated of the um elements on the right hand
  3172. 4:06:17side are slightly off. I just want you to fix  them all so they're the exact same width. On
  3173. 4:06:21the generate tab, auto prefill the generation  prompt with the user's templated prompt. Add
  3174. 4:06:26a section under inspiration thumbnail where I  could just paste an image URL and then it goes
  3175. 4:06:30and automatically populates it. Under settings,  we'll need to upload multiple reference faces. So
  3176. 4:06:36have a ability to upload more than one, not just  one. And then in the default prompt instructions,
  3177. 4:06:41this is where you'd automatically insert some  generated prompt in the generate page. So
  3178. 4:06:46whatever the user writes here, I want reflected  in the generate page by default. And then the
  3179. 4:06:50user can modify that slightly as necessary. On the  landing page, remove all references to nanobanana
  3180. 4:06:55and replace with thumbly as mentioned. Add more  social proof here because we're running out of
  3181. 4:07:00them pretty quickly as the business names scroll  to the left. Make the website landing page around
  3182. 4:07:07twice as long in general. Finally, I'll say the  app needs a major redesign. Focus on the light
  3183. 4:07:11theme as provided in the images above. Ensure  you're using the right font etc. We want light,
  3184. 4:07:21not dark. Soft glows and futuristic glass style  aesthetics. Cool. I'm now going to give it some
  3185. 4:07:32more time to make the required changes and  then I'll check back on the app. We're at the
  3186. 4:07:35next leg of that redesign. So, I'm just going  to take another peek at localhost 3000. Well,
  3187. 4:07:40it's definitely looking a lot brighter, which is  nice. Kind of weirdly yellow and green, which I
  3188. 4:07:45don't really know how much I like. Uh, let's go  to the dashboard. Ooh, this is much better. Much
  3189. 4:07:48better. I see that it's taking the inspiration  more on the actual dashboard side of things than
  3190. 4:07:53it did on the landing page. And that's okay. Okay,  cool. It also fixed that margin issue that we had
  3191. 4:07:57earlier. Um, I actually really like this. I'm just  going to zoom in a bit. Okay. I think what we need
  3192. 4:08:02to do is we need to just widen it a bit. So, I'm  going to do the same thing. Hey, this looks much
  3193. 4:08:07better. Could you widen the um elements in the  dashboard, the generate page, and the settings
  3194. 4:08:13page? I feel like they're not very wide right  now, and that just looks silly. Um also, what font
  3195. 4:08:20are we using? Are we using that provided font?  Some of the colors are a little too light now,
  3196. 4:08:26I would say, like the highlight uh color on  the left handmost navigation elements. That
  3197. 4:08:33light green or whatever it is, that neon color  is a little rough. So, I think we're probably
  3198. 4:08:39going to have to reduce that just for contrast  purposes. Um, are we using real glass isomeorphism
  3199. 4:08:44here? If you don't know what that is, um, I can  provide significantly more context. Anyway, uh,
  3200. 4:08:49we do have some major issues on the landing page  side of things. This looks pretty poor. I think
  3201. 4:08:53what I'll do is I'll just provide you a landing  page that I want you to copy verbatim like word
  3202. 4:08:57for word because just the way that you're using  shadows and stuff like that looks really silly
  3203. 4:09:01right now. Aside from that though, um, pretty well  done. I like this. I'll provide you that landing
  3204. 4:09:06page and then you can try copying it verbatim  u to start and then we can make some other
  3205. 4:09:10modifications afterwards. Here's the landing page.  Okay, that looks pretty solid. I'm just going to
  3206. 4:09:15go and I'm just going to find a really classy  isomorphism glass. Okay, glass morphism, I guess,
  3207. 4:09:24landing page. That makes more sense. Okay, we  just want one that like actually looks like a
  3208. 4:09:30like a real app, you know, not one that's BS. So,  let me take a look what has like that light theme.
  3209. 4:09:39Okay, I like this. This is pretty good. You know,  one of my favorite things to do is just to open
  3210. 4:09:43up the local dev server and then just watch  as it slowly but surely updates the page and,
  3211. 4:09:49you know, incorporates your device. It's kind  of neat. So, it's just done that up here. Um,
  3212. 4:09:53it's just using some fake logo here to try and  mimic it, but obviously it's not the same thing
  3213. 4:09:57as the actual logo. It's like adding small little  elements here or there, changing like the colors
  3214. 4:10:02and the background and and stuff like that. Um,  so that's that's pretty cool. Quite sexy. I really
  3215. 4:10:07like um being able to see that. It's doing the  same thing underneath with like the soft gradients
  3216. 4:10:11and then obviously changing the uh the colors  and stuff because some of the elements have not
  3217. 4:10:16been adjusted yet. Obviously, the background  in this case and the text is black. But yeah,
  3218. 4:10:20as it continues, it'll just get closer and  closer and cleaner to that actual pixel perfect
  3219. 4:10:24uh uh generation. Website's slowly getting  better and better. It's getting cleaner. Um
  3220. 4:10:28all these elements now are starting to match  color-wise. We even have that little down CTA
  3221. 4:10:34with that light blue. So, this is a much better  approach, I would say. Some other adjustments
  3222. 4:10:38I went through and then in uh a lot more detail  basically deconstructed everything that I wanted
  3223. 4:10:43changed. So I wanted to make the nav bar a little  bit square. I wanted to fill out the rest of the
  3224. 4:10:47dashboard underneath the hero header, make the  social proof section infinitely revolving and so
  3225. 4:10:51on and so forth. And the idea here is we just  want to get the app as close as uh possible
  3226. 4:10:55to basically perfect aesthetically speaking  before I do all the rest of the work. Okay,
  3227. 4:10:59we got the website right over here looking really  clean. Notice how we've gone through and then
  3228. 4:11:03actually adjusted the dashboard down here. That's  really, really sexy. Um, I'm not liking the slight
  3229. 4:11:08difference in Oh, actually, no. That's basically  perfect. Why don't we just, um, I think I'll
  3230. 4:11:13probably square out all the buttons everywhere.  But anyway, this stuff's looking real clean. We
  3231. 4:11:17have the pricing down below, ready to blow up your  channel. I'm just going to go to dashboard. Let's
  3232. 4:11:22just see how the actual functionality of the app  is. This looks pretty good. Um, I don't really
  3233. 4:11:27like the light blue in the back, so I'll adjust  that as well. But everything else is looking good,
  3234. 4:11:30right? Like the margins are basically all the  same. Um, we also have emphasize contrast. So
  3235. 4:11:35now the generation prompts are autopop populating.  And yeah, I mean, I'd say this is pretty great. I
  3236. 4:11:40don't like the background blue on the um inside  of the app page, like the dashboard to generate
  3237. 4:11:47the settings. That component looks weird to me.  I'd like some collection of soft gradients on the
  3238. 4:11:54background of the hero header in the landing  page. And then I'd like you to turn all pill
  3239. 4:12:02shapes right now into those rounded squares  instead. I think that just looks a lot better.
  3240. 4:12:08For instance, the signup button in the navbar,  the real-time generation from your prompts widget,
  3241. 4:12:15and the dashboard in the hero header um image. I  want all of those little pill shapes converted.
  3242. 4:12:24Aside from that, change define to thumbly. I  want you to make sure that those two buttons,
  3243. 4:12:30filter by CTR and plus new thumbnail, are just on  one line. Right now, they're both on two. Adjust
  3244. 4:12:35the verbage if necessary. And then everything  else looks really clean. Yeah, that's about
  3245. 4:12:44it. All right, this is looking a lot cleaner. We  have everything that we need on the landing page.
  3246. 4:12:49Um, I like the fact that the cards no longer  look that ugly, atrocious blue. At this point,
  3247. 4:12:54all we really have to do is provide  all of our API keys and tokens. So,
  3248. 4:12:58as mentioned, I basically want to reproduce  the functionality of AI studio.google.com,
  3249. 4:13:02except I want to be able to provide a thumbnail  and then a bunch of my own faces and then just
  3250. 4:13:06have it replace the image in the uh thumbnail, or  rather replace the person's face in the thumbnail
  3251. 4:13:11with my own. This is a pretty common thing to do  on YouTube nowadays. Basically what you do is you
  3252. 4:13:15find like outlier really high quality thumbnails  and then you just replace them and make some minor
  3253. 4:13:19adjustments. Um I'll show you guys what I mean.  If you head over to this app here, one of 10, and
  3254. 4:13:24then you go down to, I don't know, videographer or  something, and you know, just look for something
  3255. 4:13:31like this by this fella here, Kristoff Oliver. I  mean, like, is this the best thumbnail? Actually,
  3256. 4:13:36no. Let's use this one. This one's probably  nicer. So, you see how there's like, you know,
  3257. 4:13:40some fella here in the middle and then there's the  text around it and then there's some little image.
  3258. 4:13:43So, I mean, like, you know, I think you'd probably  design something better than this, but still. I'm
  3259. 4:13:46just going to save this image. Head over to AI  Studio. I wanted to just switch my account to
  3260. 4:13:51one that actually has credits. What I'm going to  do is I'm going to stick this puppy inside. Then,
  3261. 4:13:56I'll say replace the man in the thumbnail with  the man in the profile picture provided. Then, I'm
  3262. 4:14:05going to look for a picture of myself. I like this  one. This one's pretty funky. So, I'm going to
  3263. 4:14:10say replace the man in the thumbnail that includes  how to build a portfolio with a man in the profile
  3264. 4:14:17picture holding a trophy. Okay. So, what I want  basically want to do, what I'm instructed to do is
  3265. 4:14:24to take this and then just swap it out for this or  something close to that. So, I press enter. You'll
  3266. 4:14:29see that it's not going to do the most amazing  job right off the bat, but it's going to do an
  3267. 4:14:32okay job. And basically the whole idea is we're  just going to run this multiple times until we get
  3268. 4:14:37like three or four options. And then we're just  going to present them to the user and then they
  3269. 4:14:40can just select one that they really like. And  scrolling down here, you can see that we've since
  3270. 4:14:43replaced that man just with me holding my trophy.  So it didn't get like exactly what I wanted to do.
  3271. 4:14:48Obviously I don't actually want to be holding the  trophy, but you can see that I'm in this fell's
  3272. 4:14:52room. And for the most part, it looks like me. I  mean, there's some minor little changes in terms
  3273. 4:14:55of the skin texture and stuff. Um I think my skin  texture is worse and it's like done some done some
  3274. 4:14:59touch-ups, but you know, it's got my hair. It's  got me holding the trophy. didn't add any extra
  3275. 4:15:04AI fingers. And yeah, that's more or less what  we're doing, right? So the question is, how do
  3276. 4:15:08we actually do this in our app, not inside of this  as studio.google.com thing and it's pretty easy.
  3277. 4:15:13There's just like a bunch of API routes for image  generation. We just basically need to reproduce
  3278. 4:15:17the same flow that I just did here over there. And  then we need to um connect API keys and tokens and
  3279. 4:15:22stuff like that. So I have an API key over here.  Uh I'm just going to I don't know. I guess I need
  3280. 4:15:27to find a way to copy this API key. So why don't  I go to get API key here. We'll create a new one.
  3281. 4:15:31And I'm just going to call this um thumbly. Going  to click create. We're now going to have the key
  3282. 4:15:38generated right over here. Okay. And I'm just  doing this in a new one because I want to be able
  3283. 4:15:43to turn it off. I'll then go back to anti-gravity.  And then, okay, it's just done some changes for
  3284. 4:15:49me. I don't know exactly what. Then I'm going to  open up av file and then I'm going to say Gemini.
  3285. 4:15:55I think this is Gemini, right? What is this one  technically called? uh maybe like nano banana API
  3286. 4:16:02key and I'm going to paste that in. Um there are  a couple of other things that we need if you think
  3287. 4:16:07about it. So this is not enough. We obviously have  to go through the whole superbase spiel and then
  3288. 4:16:12get a bunch of images. Sorry, I get a a database  from there. So I'm going to set up a database on
  3289. 4:16:17Superbase just like I've done before. Head over to  superbase.com or rather I think it's database.new
  3290. 4:16:23is even faster, right? Yeah, there we go. I'm  going to do it inside of proposal generator.app
  3291. 4:16:28maybe gyro. Okay, never mind. I need to go and  delete one of these old ones, so bear with me
  3292. 4:16:31one second. This is in the leado database, right?  So, I'm just going to delete this project. Leadzo
  3293. 4:16:36DB. Cool. Thank you. Delete. Um, and then  I'll go to database new. Once that's done,
  3294. 4:16:44now it's going to say, hey, let's make one. I'm  going to call this one um Thumbly DB. Again,
  3295. 4:16:50I'm going to generate a password. Copy that  password over. Enable. Oh, cool. They also now
  3296. 4:16:55have automatic RLS, which is cool. So, I'm going  to create a new project there. And what I want is
  3297. 4:16:59I basically want to um paste in my database  password. Let's say superbase DB password.
  3298. 4:17:08Paste that in. Um I don't know, superbase  project URL. Paste that in. Previously, I
  3299. 4:17:14did this just directly inside of the um you know,  agent chat, but this time I'm actually going to
  3300. 4:17:17copy and paste it over to the CNV. So, Superbase  publishable API key. I'm going to paste that in.
  3301. 4:17:26I think there are a couple other ones. You know,  I just want to give it my API key as well. So,
  3302. 4:17:31we'll go superbase project ID. Paste that in.  You can see it's the same thing as in my URL. So,
  3303. 4:17:38basease project name I'm just coming up with all  excuse me, I'm just coming up with all this stuff
  3304. 4:17:45um myself. Like I'm coming up with these names  myself. Um these aren't really important. The
  3305. 4:17:49model can understand the context themselves.  Okay. So, I I have more or less all of that,
  3306. 4:17:54which is cool and pretty clean. Um, and then yeah,  now it's just provisioning my database and API
  3307. 4:17:59input. It's actually creating them for me. So once  all that stuff's good to go. I'm just going to
  3308. 4:18:04paste that in. Any other additional functionality  we need? I don't think so. So I'm going to say is
  3309. 4:18:09I've added a bunch of uh credentials for nano  banana and then superbase um into the env file.
  3310. 4:18:17You now have everything that you need in order  to actually build out the functionality of the
  3311. 4:18:20app aka the API calls. I'll go call or find the  um specific endpoint to reference. But basically,
  3312. 4:18:26we're going to be replicating the functionality  of um Google's AI Studio just inside of my app.
  3313. 4:18:33Let's see. ENV. Cool. And then, you  know, there should be the ability
  3314. 4:18:43to grab the code. Okay, cool. And there  is. So, I can grab this code. And then
  3315. 4:18:48we're just going to go rest here. And  then what I want is I basically just
  3316. 4:18:54want to copy all of this stuff. And  then I'm just going to paste this in.
  3317. 4:19:05Here is some REST code straight from their  dashboard. And then I'm just going to paste
  3318. 4:19:10this in, which should be everything that they  need in order to actually like generate the
  3319. 4:19:13the thing. Keep in mind we're going to  be supplying two inputs. The provided
  3320. 4:19:20thumbnail image and our prompt uh I guess  three inputs. The provided thumbnail image
  3321. 4:19:29um images of the person's face and then a prompt
  3322. 4:19:39check there. Let me see. Are there any docs  or something like that I could use to give
  3323. 4:19:43me more data? Okay, check their docs if  you need more on how to do this. First,
  3324. 4:19:51test all of this via curl to make sure it  works. And then once it works, you can put it
  3325. 4:19:58on the app. And then finally, I'm going to just  provide some base um data here. So, you know,
  3326. 4:20:04earlier I had that portfolio builder image. So,  I'm actually just going to supply these images.
  3327. 4:20:08Um, so this is going to be one image. I think  we can just open this in a new tab. Okay. No,
  3328. 4:20:14I guess we can't. So, let me just save the  image. This is going to be the supplied. Okay,
  3329. 4:20:23this one over here. Then I'm going to move into  anti-gravity. Just upload this to the agent. I've
  3330. 4:20:30provided you three things. supplied the image to  insert a face into um face the image to get the
  3331. 4:20:46face from and then prompt and the prompt is going  to be here. Let's just save this too. Uh this is
  3332. 4:20:56pretty big actually. I don't know if we'll be  able to feed all this stuff in. Let's say face
  3333. 4:21:05And uh it should be able to pull all  of this data up from just the names.
  3334. 4:21:11Okay. In case like unless we get blocked, we  should be good. Just going to double check this
  3335. 4:21:17because we we have supplied like a lot of image  files here. I mean this was like 4 megabytes.
  3336. 4:21:21This here was like I don't know megabytes. So  in total it's going to be like five or six megs
  3337. 4:21:25which is actually pretty chunky. Maybe they like  automatically resize the images or something so
  3338. 4:21:29it's not taking up a massive amount of tokens. But  um you know I always do kind of worry like oh am I
  3339. 4:21:33going to run out of usage and stuff. Okay. So I'm  gonna allow this conversation. It can do more or
  3340. 4:21:37less whatever the heck it wants. And then um just  double checking thumbly. Yeah. I mean like this
  3341. 4:21:46honestly looks really clean. I'm liking this quite  a bit. Nice. And then we have like this infinitely
  3342. 4:21:50revolving social proof section here which you know  you stick your own social proof in. And then all
  3343. 4:21:55of the um buttons and stuff like that are square  now which is cool. And everything is just a little
  3344. 4:22:00bit more squared off. I don't actually like this  shadow. There's a slight shadow in the background
  3345. 4:22:03here, which hurts, but not the end of the world.  We have the ability to change this. This is nice.
  3346. 4:22:08Cool, cool, cool. Awesome. I mean, like, you know,  I think this is basically like the the MVP of
  3347. 4:22:13um a high quality app with the landing page. So,  wonderful. I'm just going to wait and then um let
  3348. 4:22:18you guys know when we're done this next step.  Looks like it's already making API calls, which
  3349. 4:22:22is cool. Just using everything that I provided it  below. Generative language. Google APIs appears
  3350. 4:22:27to be the endpoint. That's pretty nice. And  so it's gone through and actually verified
  3351. 4:22:30that this works and it's created um another step  inside of implementation plan. So now it's going
  3352. 4:22:35through and then integrating this directly into  the app. So it's not just going to be doing it
  3353. 4:22:39via its own curl requests, but I'll be able to do  it via uploads files and stuff like that. Okay. So
  3354. 4:22:44just signing in here. We've now integrated the  um database functionality. Going to go over to
  3355. 4:22:49generate and see if we can do this. So you know  I can obviously add images and we just did. So
  3356. 4:22:54now we have this cool little blur effect which is  really nice. Let me see. Keep the style identical
  3357. 4:22:59to the inspiration image. Make the main subject  highly cinematic with dramatic neon backlighting.
  3358. 4:23:03Contrast. So no, I'm going to say but replace  with the user. Oh sh uh crap. I need to actually
  3359. 4:23:09provide images, right? So let's upload some faces.  Let's do face. This is now me. Okay. And then here
  3360. 4:23:17inside of the default prompt instructions, I'll  say replace the thumbnail image with the supplied
  3361. 4:23:24user cinematic. and I don't know dramatic lighting  on the face. Replace the face of the person in the
  3362. 4:23:36provided thumbnail image with the face of the  supplied user. Cinematic and dramatic lighting
  3363. 4:23:42on the face. Let's save the config. I'm just  going to refresh this. Has that been saved? Okay,
  3364. 4:23:46it is. This has been saved as well. Okay, that's  great. You know, might as well test one additional
  3365. 4:23:51piece of functionality here, which is if I could  just paste the URL in. So let's go back here,
  3366. 4:23:57paste that in. Okay, cool. So we've actually  we've actually now got this in the URL, too,
  3367. 4:24:00which is clean. I'm going to click generate  variance. And this is really like the test
  3368. 4:24:05of the functionality. So I'm going to give  it a few seconds. Then I'll double back with
  3369. 4:24:09um you know, changes if it didn't work, and  then maybe some next steps if it did. Okay,
  3370. 4:24:13we've actually generated one of the options here,  and it looks interesting. Um for whatever reason,
  3371. 4:24:19look, it's like the background's kind of white. I  don't know. And we've only done one, so we want to
  3372. 4:24:23do three, right? Obviously, we're going to want  three. I see there's some click functionality,
  3373. 4:24:27which is kind of cool, but um yeah, we're going to  have to do more. So, the first thing I mean, the
  3374. 4:24:32dramatic lighting looks freaking badass. Like, you  know, it's not exactly my nose, to be honest. It's
  3375. 4:24:37a little bit different for me, but still really  cool. Hey, we've um generated only one, not three.
  3376. 4:24:43So, just double check and make sure that there  was no issue in the background that prevented us
  3377. 4:24:47from doing um all three simultaneously because we  want to populate that with three thumbnail images,
  3378. 4:24:52not just one. Also, when the images came out, they  had this sort of like white sheen or overlay. They
  3379. 4:24:59looked kind of transparent. I just want you to  remove that. Um, so that I just can see the actual
  3380. 4:25:04image immediately. Uh, and yeah, I think that's  about it. What's interesting is while it did that,
  3381. 4:25:10it consumed three credits. Okay, so the credit  consumption functionality is there. However,
  3382. 4:25:14when I saved this, it saved it twice. So, that's  another thing we'll have to change. This time
  3383. 4:25:19we're going to do the same thing just with the  supplied version instead. And then I should just
  3384. 4:25:24be able to click generate variance and we should  be able to do three, right? Since we're generating
  3385. 4:25:28three times. So credits available um on the left  hand side, which you guys can't see. Say 197 right
  3386. 4:25:34now. Okay, now we have three provided variants.  These all look awesome. I'm loving this. Loving
  3387. 4:25:39the the really badass lighting on the face. That's  neat. Um so now what I'm going to do is I'm just
  3388. 4:25:42going to select one of the variants that I want  to keep. So why don't I select this one? That one
  3389. 4:25:45looks probably the most realistically me anyway.  And then I'll click keep selected thumbnail. It
  3390. 4:25:50says thumbnails saved to your gallery, which is  awesome. Okay. And then we go back to overview.
  3391. 4:25:54And then we can see this new one here. Beautiful.  Okay. So, I guess what else we need? Like the
  3392. 4:25:58first thing comes to mind is we just need a way to  like delete these, right? Provide a way to delete
  3393. 4:26:03um the thumbnails under recent generations.  Basically, I want to be able to delete ones
  3394. 4:26:07in my gallery so that I don't have to see them in  the database anymore. Um aside from that though,
  3395. 4:26:11everything looks like it worked really clean. Oh,  um, instead of like the alert that comes up, um,
  3396. 4:26:16just make like a nice modal, a nice toast message,  um, that then allows you to, um, I don't know,
  3397. 4:26:23open it in a new tab or download the image or, uh,  go back and generate a new one. Also, just little
  3398. 4:26:28things. I mean, these intelligences are so dang  good. Notice how in this one here, I don't have
  3399. 4:26:32the O behind my neck, but in this one, I I do.  Like, it's, you know, it knows the placement of
  3400. 4:26:37the O and where it should be and stuff like that.  But yeah, um now that we're done with all this,
  3401. 4:26:41what we're also going to do is we're going to  uh like after we get the little X functionality,
  3402. 4:26:46we're going to hook this up to Superbase and then  it's just going to give me that migration script
  3403. 4:26:50so that I could use this in like real production  scenarios. Then on from there, it's connecting
  3404. 4:26:55it to Stripe so that the payments work and then  yeah, everything's just going to be 100% live,
  3405. 4:26:58which I'm really excited for. Speaking of Stripe,  I forgot, but I do need to provide the keys there
  3406. 4:27:02as well. So, let me head over to Stripe, sign  into that sandbox. It's right over here. And then
  3407. 4:27:07I'll give both the publishable key and then secret  key. So stripe publishable key, stripe secret key.
  3408. 4:27:18Then I'm just going to save this and say, hey,  I've also added the Stripe publishable key and
  3409. 4:27:22Stripe secret key. I want you to connect the  payment feature as well. You may have to adjust
  3410. 4:27:29the SQL migration script. So um do this first.  Okay. And the really cool thing is I can just
  3411. 4:27:36queue up messages. So even if I change my mind  or do a bunch of things, I can have this message
  3412. 4:27:40sent. I can then read that message and then just  um incorporate it in the flow. I don't actually
  3413. 4:27:44have to wait until it it all finishes. So that's  pretty clean, huh? Pretty stoked about that.
  3414. 4:27:48While we're waiting, why don't we test this on  another thumbnail? So I'm going to head back over
  3415. 4:27:52to generate and then I'm going to paste this in.  Going to set that. I'll say replace the face in
  3416. 4:27:57the provided thumbnail which is the face applied  to use cinematic and dramatic landing the face.
  3417. 4:28:00Also replace 100 to 1,000. Let's see if maybe we  could get um a slight little variant of the actual
  3418. 4:28:08number in the background as well. Generally  speaking, my experience with these AI models,
  3419. 4:28:12you only really want to suggest one major change  at a time. So maybe what I could also do is add
  3420. 4:28:16like a little tips feature or something like that  so that people know um how to prompt these things
  3421. 4:28:20and get the best results. Nothing like clean work.  This one here looks real good. I like it. We have
  3422. 4:28:26the 1000 in the background. Also dramatic lighting  on the face. That's cool. And this one has
  3423. 4:28:30dramatic lighting on the face with my actual skin  texture. Thank you, Rosa. Um, honestly, I think
  3424. 4:28:35all all three of these are really badass. So, I'm  going to keep this one. And as you can see, I'm
  3425. 4:28:39going to have a toast message instead. So, I can  download this image. I can open in a new tab. Uh,
  3426. 4:28:44that one doesn't seem to work, so I'm going to  have to modify that. And then I can also click
  3427. 4:28:47generate another. It'll take me back to this page.  So, really, really clean functionality. I mean,
  3428. 4:28:50this is basically exactly what I wanted. Just  wish it could be packaged in a slightly better UX,
  3429. 4:28:54but we'll we'll solve that later. It's now going  through and just doing a bunch of Stripe stuff.
  3430. 4:28:57So, creating API routes, resolving TypeScript  errors, and so on and so forth. I'll let it go
  3431. 4:29:01and just do that thing. um as it wills and then  we'll double check how all that works with SQL
  3432. 4:29:06and we're done with that. Okay. Now I'm going to  use the uh big thing inside of Superbase schema
  3433. 4:29:12migration script the file that it created for  me. Then just hold command and press enter. I
  3434. 4:29:18realize I used to think that you couldn't have  comments in here but uh you can. It's just the
  3435. 4:29:21comments that the previous model did for me  were I think like with two hashtags instead of
  3436. 4:29:26um two dashes. As long as there are two dashes,  you can basically pump this whole thing in and
  3437. 4:29:30there are no problems. And it's always good  once you're done with that just to go back
  3438. 4:29:32to database and then you can see how everything  interacts. So see the model here is set up ID,
  3439. 4:29:36user ID, original image base 64, prompt, generated  URL, selected URL, and created at as well as ID,
  3440. 4:29:42email, credits, Stripe, customer ID, subscription  ID, default prompt, face images B 64, and then
  3441. 4:29:48created at. This is where we're basically going  to store their status. Okay? And then over here is
  3442. 4:29:54where we're going to store the number of credits  that they have. So if they have a subscription ID,
  3443. 4:29:57then they will have been signed up. Um,  obviously if they have credits, any credits,
  3444. 4:30:01then we'll populate that. That's where we're going  to get this from. Um, and then if they're at zero
  3445. 4:30:05credits, then when they attempt to make a thing,  it'll check their credit balance. And, you know,
  3446. 4:30:09because they don't have any credits, that won't be  able to uh work. The primary key of thumbnails is
  3447. 4:30:13ID. Primary key of users is ID. These two things  are sort of mapped together. And then, yeah,
  3448. 4:30:18everything else here looks pretty solid to me.  So, just heading back to anti-gravity. Right now,
  3449. 4:30:21what it's doing is just finishing up that little  migration from uh mock routes, which are when
  3450. 4:30:27you store all of the database files and like, you  know, your your local computer to ultimately like
  3451. 4:30:32live supabbase instances. And it's just doing a  build right now to verify that everything works
  3452. 4:30:37uh the way that we told it to do it. And as you  can see, I've just signed into this supposed new
  3453. 4:30:42account here and uh we are now at zero credits  available. So, it's pulling it directly from the
  3454. 4:30:47database. Meaning if we want to run the full flow,  we now have to go through create a new account
  3455. 4:30:52and then run basically the entire signup flow.  So I'm just going to go back to anti-gravity,
  3456. 4:30:58verify that everything is good. Awesome. Live  database has now replaced our prototype API
  3457. 4:31:03structure. I've now done it all. So we should be  able to test this. Just going to head back first
  3458. 4:31:09to Superbase and then I'm going to turn off the  feature of authentication that forces us to um
  3459. 4:31:14confirm our email. So you can do that in signin. I  just do that because it's a little bit faster. And
  3460. 4:31:18I realized after that first build, I was spending  just as much time, you know, signing up as I was
  3461. 4:31:23doing everything else. Now I'm going to click  sign up. And this is sort of the desired user
  3462. 4:31:26flow. So we'll go [email protected]. Continue with  email. Let's see what happens. Just says signing
  3463. 4:31:31in. There's no password. So this is a problem. Um,  notice how before we always had an email address
  3464. 4:31:35and a password. Now we just have this like email.  So I think this is probably a blind spot where it
  3465. 4:31:40didn't really realize, oh, okay, we're connected  to Superbase. Now we have O. So we're going to
  3466. 4:31:43need an actual like login page. Hey, the login  right now only requests an email, but I need to
  3467. 4:31:49authenticate with Superbase. I'm pretty sure we'd  need an email and a password. No, I just tried
  3468. 4:31:53to create one and it didn't really work. There  were some errors. Okay, so now going to see if
  3469. 4:32:00maybe I'm already logged in or something.  We go to payment. Yeah, no, we can't. So,
  3470. 4:32:05I mean like the middleware routes are working as  we could tell with dashboard and stuff like that.
  3471. 4:32:08Everything redirects us to login. It's just the  actual login doesn't seem to be um set up yet. So,
  3472. 4:32:13we'll double click that. We'll double check that.  Um, it looks like we also added some additional
  3473. 4:32:18landing page stuff here, which is super cool. So,  this added a whole new section based off what we
  3474. 4:32:22added. AI power generation, AB testing, clean  modern aesthetics, and so on and so forth. We
  3475. 4:32:27also have some FAQs here based off how it works.  So, that's really cool. And then we have the ready
  3476. 4:32:32to blow up your channel. Um, Gemini will do this  from now and uh every now and then. I don't really
  3477. 4:32:38sometimes it's sort of annoying when it acts  without necessarily asking you, but in this case
  3478. 4:32:42it was what I wanted because really really early  on in the prompt I said, "Hey, I want you to make
  3479. 4:32:46this longer." And then it said something like,  "Oh, I don't have enough context to make this
  3480. 4:32:49longer." So I guess it just like generated its own  context based off of our conversation history. One
  3481. 4:32:53thing I really like about this app is just how  fast it is. I mean, each of these routes are what
  3482. 4:32:58are called preloaded or pre-filled. And so this  is me like really quickly going from one page to
  3483. 4:33:02the other. And just notice how this whole page is  just like automatically done. Um, I also really
  3484. 4:33:06like these brief little animations where you, you  know, start at the top and work your way down,
  3485. 4:33:10loading each element slowly in succession. You  just get the, uh, visual appearance of very fast,
  3486. 4:33:15very performant website. Okay, we have some  new superbase schema. So, I'm just going to
  3487. 4:33:19jump over here and then what this is going to do  is go through and then add the rest of our users,
  3488. 4:33:25tables, and stuff like that. So, back to SQL  editor, paste this in, run. Okay, the updated SQL
  3489. 4:33:31script seems to have worked. So, I think we just  added one or two additional records here and then
  3490. 4:33:36allowed it to add like the email and the password.  Heading back to Thumbly, if I go click sign up,
  3491. 4:33:42we're running into Superbase URL is required.  So, they do have some runtime error. Now, I'm
  3492. 4:33:47just going to paste all of this in. Okay, this new  signup page seems to work. We'll go nickniki.com.
  3493. 4:33:54Then, Nickniki. Um, I'm going to click sign in.  Invalid login credentials. The reason why it's
  3494. 4:33:59telling me this is because we obviously don't have  an account. So, I'm going to go back to sign up
  3495. 4:34:02instead. I like that it keeps the email address  and the password. I don't have to redo it. Okay,
  3496. 4:34:07we now have the secure checkout with the starter  plan with 100 thumbly credits. So, now what I
  3497. 4:34:11can do Okay, because we're we clicked the starter  plan. So, I can go Oh, actually, did we click the
  3498. 4:34:17starter plan? Hold on one sec. I don't necessarily  just want to buy the starter plan. I might want to
  3499. 4:34:22buy pro. Let me try agency, actually. Okay, we'll  go nickniki.com. And do we have the account? Oh,
  3500. 4:34:30you see because we exited out of the um payment  flow, it immediately jumped us into dashboard, but
  3501. 4:34:40it selected the starter plan automatically. So, I  need to change that. Right now, it's automatically
  3502. 4:34:45selecting the starter plan. You should allow the  user to select which plan they want on the payment
  3503. 4:34:50page. It should also take into account which  button they click on the landing page because
  3504. 4:34:55there are three different payment options there  as well. Just going to enter this in and then
  3505. 4:35:00I'm going to proceed to check out just to see  what happens. When I click proceed to checkout,
  3506. 4:35:05nothing occurs. And I think the reason why is  there might be some problem here. Additionally,
  3507. 4:35:11when I click proceed to payment, nothing occurs.  Do we need to open up a Stripe checkout window or
  3508. 4:35:16is the payment occurring locally on the platform?  Keep in mind, I'm using a Stripe sandbox, so we
  3509. 4:35:21should be able to test the payment and have all  of the events and stuff like that run true. Hey,
  3510. 4:35:25more pointedly, um, since I am now signed in, I  should be able to go to the dashboard even though
  3511. 4:35:28I haven't done the payment. If I go to overview  and then click generate new and then actually go
  3512. 4:35:34down to settings, can I upload my face? So, we go  supplied face. Okay. And I'm just going to refresh
  3513. 4:35:41this. Am I still here? Okay. So, I'm not actually  keeping the reference faces in. And this could be
  3514. 4:35:46because my account is not like set up yet because  the payment hasn't gone through. I'm not entirely
  3515. 4:35:50sure. Let me just make sure everything else works  here. So, face that goes through. All right.
  3516. 4:35:54If I click generate variance, what's going to  happen? Please provide an inspiration image and
  3517. 4:35:58a prompt. So I have the inspiration image here.  The prompt is right over here. So we also have an
  3518. 4:36:04erroneous error message where it says please  provide an inspiration image and a prompt. Hey,
  3519. 4:36:08I provided an inspiration thumbnail and a  generation prompt. And I clicked generate
  3520. 4:36:12variance, but I'm getting an error called please  provide an inspiration image and a prompt. I think
  3521. 4:36:16this is occurring because I don't have a reference  face. However, that error is not representative of
  3522. 4:36:22the real problem. If this are if this is the case,  I've also noticed that when I click upload face on
  3523. 4:36:27reference face, then I click save configuration,  nothing happens. And then if I refresh,
  3524. 4:36:33my reference face is gone. So make sure that  the save configuration button works. If it's
  3525. 4:36:38not working because of some frontend error,  fix that. If it has to do with superbase,
  3526. 4:36:45let me know if there's anything I need to do on my  end. And I'm just going to continue going through
  3527. 4:36:48this and seeing if there are any other errors  that I could spot. Obviously, I'm going to sign
  3528. 4:36:52out again because I'm on a local dev server. This  is all occurring in real time. So, any updates I
  3529. 4:36:56make to this is going to be reflected. Um, but we  do need to make sure that if credits available are
  3530. 4:37:01zero that we immediately jump back, right? So,  some other design decision. If a user has zero
  3531. 4:37:05credits upon signin, we need to redirect them to a  payment page where they could select um, you know,
  3532. 4:37:10how many credits to purchase and stuff like that.  That should occur every time a user is at zero.
  3533. 4:37:15Now, if you're noticing, I'm not actually  just like doing waiting, checking the feature,
  3534. 4:37:21and then proceeding to the next one. I'm now  at the point where I'm just dumping in a bunch
  3535. 4:37:24of changes. And the reason why is because most of  these changes are relatively minor. Uh, you know,
  3536. 4:37:28it's probably just some slight little database  misconfiguration or whatever. And so, I can
  3537. 4:37:31actually proceed in this way. Um, have it working  on a change while I'm like modifying the rest
  3538. 4:37:36of it. On the landing page under everything you  need to win the click, I don't like the shadows
  3539. 4:37:43in general. I'd actually like you just to remove  shadows across the entire UX of the website. It
  3540. 4:37:47they just seem a little bit off um given the fact  that most of the website does not have shadows and
  3541. 4:37:52does not use them. Under the frequently asked  questions where it says how does thumbly insert
  3542. 4:37:56my face? Can I use any images inspiration etc. The  title text is good. So how does Thumbly insert my
  3543. 4:38:04face? Is written in like this nice black text,  but the subtext that says when you upload your
  3544. 4:38:09reference photos in the dashboard settings, our  models learn your facial features. That's a little
  3545. 4:38:14too dark. Can you lighten that just by 10% or so?  In this way, I'm sort of arbiting the time between
  3546. 4:38:19the changes that are occurring here and then um  you know my testing. So, signing in, going back
  3547. 4:38:24to the dashboard. Let's go to top up. Okay, cool.  And now we have the ability to select these three
  3548. 4:38:28different plans, which is cool. Okay, so why don't  we pretend I'm doing pro. And then every time I
  3549. 4:38:32click redirecting to Stripe, looks like there's  this problem which pops up. So, I'm actually going
  3550. 4:38:35to copy this over then say every time I try making  a payment by clicking the proceed to checkout
  3551. 4:38:41page, this error occurs. But I mean like you know  we could also parallelize this and do a bunch of
  3552. 4:38:45them simultaneously. No real need. Um but yeah I  mean like you know we're getting closer for sure.
  3553. 4:38:50One other change it just made is when I click on  starter you see it goes payment question mark plan
  3554. 4:38:54equals starter. So I'm actually on starter but if  I go pro it actually opens up this page to pro.
  3555. 4:39:00So these links do something now which is kind of  cool, right? I can actually click get started and
  3556. 4:39:04then go to a specific payment page. I'm unsure  if this is because I'm logged in or logged out
  3557. 4:39:09though. I'm going to click sign out. Then I'll  go back here and then see what happens. Okay,
  3558. 4:39:13so login question mark plan equals pro. That  means it's actually going to keep and conserve
  3559. 4:39:18this query parameter as I browse through the  rest of the website, which is pretty neat. Okay,
  3560. 4:39:21now the redirection script has changed. It's  pretty clean. The way that this always works is
  3561. 4:39:25you can just put in whatever um numbers you want  so long as your card details are 4242 repeating.
  3562. 4:39:30So I'm just going to click pay. Please do not save  this card because it doesn't work or exist. And
  3563. 4:39:37it looks like after the payment, we're being sent  back to the main page. So, I'm just going to say,
  3564. 4:39:41"Hey, it looks like the Stripe Checkout payment  um went through, but then it redirected me to the
  3565. 4:39:47slash payment route." Uh, if I go to dashboard, it  continuously pushes me back to that route despite
  3566. 4:39:54the fact that I've already made the payment. So,  we just need to find a way to validate that the
  3567. 4:39:58user's actually done the payment. That seems to  be the main block right now. Okay, it's telling
  3568. 4:40:02me that it's finished this, which is cool with new  secure endpoints and session IDs and stuff like
  3569. 4:40:06that. Okay, I'm just going to try a new account  here and see if maybe there's a problem with
  3570. 4:40:10that. Maybe it just has to do with the fact that  I had an old account and it's redirecting me based
  3571. 4:40:15off some old flag. Then I'll click processing  there. That payment looks good. No, it must be
  3572. 4:40:20a more broad issue. So, check out Stripe here.  It looks like we are receiving the payments. So,
  3573. 4:40:26that's going through. Um, for whatever reason,  we're not actually capable of connecting that back
  3574. 4:40:30to a person. This is my fake card, [email protected].  I've made tons of payments. Uh, I'm just going to
  3575. 4:40:36relay this information over to my agent. If agents  have a hard time dealing with stuff like this,
  3576. 4:40:41it's best just to give them as much context as  humanly possible so they don't get stuck on one
  3577. 4:40:44loop over and over and over again. Okay, looks  like I've finally made it into the dashboard. So,
  3578. 4:40:49we finally solved that persistent error um to do  with payments. As I'm sure you guys can imagine,
  3579. 4:40:53you know, adding payments is like adding  another whole u problem that you have to solve,
  3580. 4:40:57which is why I wanted to push it off as long as  possible. But, uh, now that we have I'm seeing
  3581. 4:41:01that the credit monitoring is good, settings  look good. But I'm going to try uploading
  3582. 4:41:05faces. See if we could um diagnose any issues  there. The saving configuration button looks
  3583. 4:41:11like it works if I refresh this now. Okay.  No. So, it's telling Oh, okay. Cool, cool,
  3584. 4:41:17cool. I got worried there for a second, but I  guess we had a bit of a lag. Um, that's okay.
  3585. 4:41:21Okay. Going to take a peek at an example. Why  don't we just go to thumbnail generated? Oh,
  3586. 4:41:29no. That's uh that's me from before. Let's do this  one here. And then um it doesn't look like we're
  3587. 4:41:36saving the prompt variants. That's one change. I'm  also noticing this is significantly laggier than
  3588. 4:41:41it was before. Uh make the main subject highly  cinematic. Replace the face with the face of
  3589. 4:41:52the supplied face of the reference image. Use  dramatic cinematic lighting on the face. Okay,
  3590. 4:42:01let me try saving this configuration. Just seeing  if maybe it's an error or if maybe I didn't fully
  3591. 4:42:06understand what this is doing. If I refresh this  now, do we have that default prompt down below or
  3592. 4:42:13does that need to be dealt with as well? And why  is it so laggy? It may just be my computer. I am
  3593. 4:42:18editing a bunch of videos. So, okay, that doesn't  look like that filled in, which is unfortunate.
  3594. 4:42:23Um, why don't we do supplied here? Generate new  variants. Okay. Make sure the generation prompt
  3595. 4:42:31auto prefills with the default prompt in settings.  Right now it isn't. It should pull directly from
  3596. 4:42:38the default prompt instructions. It's also  a little laggy. The app takes significantly
  3597. 4:42:44longer to load now than it used to. Diagnose  whether this is because of some persistent error
  3598. 4:42:50behind the scenes or some issue with prefilling  or something else. Okay, taking a peek at this.
  3599. 4:42:56It did give me a very sexy beard. Let's be real.  Nick definitely can't grow that level of facial
  3600. 4:43:01hair. But now like the internet will be able to  tell the difference. Cue that one up. Thank you
  3601. 4:43:06very much. After the save, it's going to pop up  this little thumbnail saved. Um let's download the
  3602. 4:43:16download the image and just see how that looks.  See if there are any problems there at all. Nope.
  3603. 4:43:20That looks like definitely fake Universe Nick,  which is what we wanted. I'll go back to generate
  3604. 4:43:25another. Now I can do more. Okay. And it looks  like this is taking some time to load. I mean,
  3605. 4:43:30it's saying zero. Okay. Now it's saying 97. I  think I know the problem. I think in order to
  3606. 4:43:34fix whatever payment BS that it had to do, it's  now fetching data from the database on every page
  3607. 4:43:40load, which is adding a fair amount of latency and  then causing the app to lag a lot more. So, it's
  3608. 4:43:45obviously not what we want, but it's what's going  on. That's why every time I load settings, it
  3609. 4:43:49takes a second before this comes in. Ideally, what  you want to happen in a full stack app like this,
  3610. 4:43:54at least a modern full stack app, is when you sign  in, you want it to automatically cache and then
  3611. 4:43:58like like pull all the data and then cache it.  Um, and then that way everything is pre-filled,
  3612. 4:44:03all the images are prefilled, the credit amounts  prefilled, so on and so forth. And then instead,
  3613. 4:44:06what you want is you basically only ever want that  to change if you materially change the database.
  3614. 4:44:11So when you change a database, then it says,  hey, you know, you should probably grab the new
  3615. 4:44:15data as well, just uh just to be 100% sure. And in  Nex, they manage this through a variety of means,
  3616. 4:44:20but a big one is like mutating the database um  or or setting like mutations or or whatever as
  3617. 4:44:25opposed to always fetching totally new data. So,  I think that's what's going on. I'm just going
  3618. 4:44:29to instruct the agent, see if we could fix that,  and then assuming that there's no other changes,
  3619. 4:44:33I'm just going to push this puppy live. Okay,  looks like it's loading significantly faster now,
  3620. 4:44:37which is nice. We can jump around from settings  to generate to overview, and we don't have that
  3621. 4:44:41like really persistent lag like we had before.  Um, we also have the ability to, you know,
  3622. 4:44:45delete if we wanted to. I think what I'm going  to do is I'm just going to open this in, well,
  3623. 4:44:50not an incognito window. I guess I'll just open  it in a new tab. And then what I want to do,
  3624. 4:44:54whoa, I don't know what the hell just happened  here. No, thank you. Let's not do that. Thank
  3625. 4:44:58you. Thank you. Um, I think what I'm going to do  is I'm just going to try the mobile features now
  3626. 4:45:03on the dashboard because mobile optimization is  pretty big, right? Just want to make sure this is
  3627. 4:45:08going to work. And it looks like it is. We have um  we have a little nav bar down at the bottom now,
  3628. 4:45:13which is kind of cool. And we can jump back and  forth between these three. So, that's nice. I am
  3629. 4:45:18a fan. Thank you. And now, let's just exit out  of the dashboard, go back to the landing page,
  3630. 4:45:23and just see what we're looking at. So, looks  like that mobile optimization prompt worked in
  3631. 4:45:27so far that, you know, the um little section here  is mobile optimized. And then all this stuff's
  3632. 4:45:34mobile optimized. I'm just going to pretend sign  in now. Okay. Okay. And then yeah, we immediately
  3633. 4:45:39jump to dashboard where we have functionality.  Let me just try deleting this. Yeah, I want to
  3634. 4:45:43delete it. And then if I just refresh this puppy,  is it gone? No, it's not gone. So that's the final
  3635. 4:45:50change we need to make. And then uh yeah, I'm  pushing this puppy live. In addition, I've also
  3636. 4:45:55set this up. So it's now at thumbly-g.netfi.app.  I just said, "Hey, put this puppy on GitHub and
  3637. 4:46:00Netlefi. Let's do this thing." And uh yeah, this  is actually working really, really good. So,
  3638. 4:46:05I'm just going to go over to sign up here and I'm  going to go [email protected]. Would be a hell of
  3639. 4:46:10a name if I could pull that up, though. And then  we'll go proceed to checkout and I'm just going to
  3640. 4:46:15enter some info. Apparently, my card holder name  is 234234. Take that, Nicholas. This has jumped
  3641. 4:46:21us directly over to dashboard and now I have the  ability to do everything. So, I'm going to upload
  3642. 4:46:26some face. Uh, what was it again? Was it supplied?  Yes, it was. Keep the identical to the inspiration
  3643. 4:46:32image. Replace the face. to face the reference  image. Use dramatic cinematic lighting on the
  3644. 4:46:35face. Cool. I'm just going to save this. Says  that it saves successfully. Oh, hold on a second.
  3645. 4:46:40That's not my face. That's my face. Good god,  Nick. You know, you've been developing an app for
  3646. 4:46:47a long time when you start making trivial errors  like that, huh? Okay, now I'm going to generate
  3647. 4:46:53three variants. Um, we're going to see how  long this takes. So, counting down. 1 2 3 4 22.
  3648. 4:47:01Okay, so right at 22, we had an unexpected error  occurred. So I imagine this probably actually went
  3649. 4:47:06all the way through. There was just some problem  with updating the DB. Uh this occurs as mentioned
  3650. 4:47:11when you go from local to some sort of like  cloud setup or or you know actually like hosting
  3651. 4:47:16it live. So I'm going to go through and just give  this an unexpected error occurred. Do a little bit
  3652. 4:47:21more final debugging and see what we need to do  to make this puppy. I would imagine the issue is
  3653. 4:47:26probably related to the fact that um when we were  running this locally, we didn't have a timeout,
  3654. 4:47:31but services that like manage the calls  for you, like uh Netlefi, for instance,
  3655. 4:47:38typically have timeouts of like 15 seconds or so,  maybe 20 seconds. So, I think we probably just
  3656. 4:47:43ran into that. Okay, just ran out of usage again  after developing this for a good hour or so. So,
  3657. 4:47:47I've moved over to Claude Code. Uh I'm still going  to try pushing and generating the variants here.
  3658. 4:47:52We're going to see how that goes. 22 Mississippi,  23 Mississippi, 24 Mississippi, 25 Mississippi, 26
  3659. 4:47:59Mississippi. Okay, so right at 26 seconds is when  we got the result. Um, I imagine that's probably
  3660. 4:48:04why this one's kind of weird. I think that's the  first one that's like actually objectively failed.
  3661. 4:48:09Uh, but yeah, no, I like this one. So, why don't  we just keep selected thumbnail? Awesome. Looks
  3662. 4:48:13clean as per usual. And uh, yeah, I mean like  we'll just click generate another and we can just
  3663. 4:48:17keep on going as many times as need be. But that's  it. We just launched our app and it works. And
  3664. 4:48:25there's one final thing we need to do, which is  that god darn security audit. Almost forgot. So,
  3665. 4:48:29let's do that. Okay, pasting this directly into  cloud code. As we can see here, now reading all
  3666. 4:48:34the client pages and doing the config. And let's  see how we do. And it's just building to verify
  3667. 4:48:39that everything compiles now. And then I'm going  to do a final check just make sure that, you know,
  3668. 4:48:44the app functionality works the way I want it to.  You'll quickly realize that the vast majority of
  3669. 4:48:48time that you spend on this is not actually the  building. It is just the giving of vibes plus the
  3670. 4:48:56verifying it works to the way your vibes require  it working. So I made a bunch of these changes. Um
  3671. 4:49:03okay, there's some rate limiting off middleware.  Okay, so I'm just going to say implement the
  3672. 4:49:10middleware with check stripe web hook secret etc.  So I'll probably have to go and grab some stripe
  3673. 4:49:20stuff, but I'm just going to go and verify that  this actually works now. Awesome. We still have
  3674. 4:49:23the ability to do everything that we had before,  which is nice. Okay, I'm taking a look at this
  3675. 4:49:29is so interesting. Like if you really zoom into  one of these things, you see every little pixel
  3676. 4:49:33that this constructed. It's wild. Um anyway, I  mean like that dead inside completely. But yeah,
  3677. 4:49:40uh we're now going to run a with check migration  on the database. So that's going to be cool. And
  3678. 4:49:45then we'll also add some web hook secrets. So I'm  going to head over there and then just verify that
  3679. 4:49:49um I got all this. Okay. Well, that one took a  little bit longer than I wanted it to because
  3680. 4:49:53we did have a bunch of back and forth with  the payments on Stripe, but suffice to say,
  3681. 4:49:57still good to go. Uh this is a good example now of  everything. It's not only, you know, kind of CRUD
  3682. 4:50:02create, read, update, delete, like a traditional  app. Doesn't just do stuff that you ask it to. We
  3683. 4:50:07also, um, are wrapping around a pretty popular  and powerful API, the Nano Banana API. And then
  3684. 4:50:13we're applying some prompts and then some sort of  creative applications here to generate really cool
  3685. 4:50:18outputs. Uh, and then we're wrapping it all in a  really nice UX and connecting it to payments. So,
  3686. 4:50:22at this point, like you guys basically have  everything that you need in order to just build
  3687. 4:50:25whatever full stack app you want. Uh, I think  what I'm going to do next is just do one final app
  3688. 4:50:29combining everything that we talked about. Maybe  make the UX a little bit more complicated. So,
  3689. 4:50:33instead of just having three or four, you know,  two or three things on the left hand side, we have
  3690. 4:50:36like what might uh be considered more of like, you  know, like a really successful enterprise app. And
  3691. 4:50:42then I'm just going to run through the motions  that I've already showed you guys multiple times
  3692. 4:50:45at this point before talking a little bit about  the economics of vibe coding and then wrapping up.
  3693. 4:50:50Man, I am so excited for this app because as  somebody that produces a tremendous amount of
  3694. 4:50:54content nowadays, having an app that can basically  allow you to focus on one uh place, let's say
  3695. 4:50:59YouTube or maybe your blog or something and then  have that same content, the same concepts and
  3696. 4:51:05ideas immediately distributed to a bunch of other  platforms is fantastic. My issue with the way that
  3697. 4:51:10most people do this is they just do it in a really  poor way. And so, you know, the end uh output
  3698. 4:51:15quality of, let's say, a blog post converted to  like Xthread snippets or whatever ends up being
  3699. 4:51:20so bad that, you know, the AI slop um overruns it  and then the quality is really poor. So, my idea
  3700. 4:51:25today is I want to make an app that's so dang good  that, you know, you don't get that. And it's still
  3701. 4:51:30written in your tone of voice. It's written really  succinctly. It's written really intelligently.
  3702. 4:51:34And I was trying to come up with like a good  name for this app just before, you know, like
  3703. 4:51:38clearly if you guys have paid attention so far,  the names so far have been afterthoughts, right?
  3704. 4:51:42But um this time I think I already got one. It's  going to be called splinter. And the idea is okay,
  3705. 4:51:48you're going to put in one piece of content which  why don't we just call this like pillar content.
  3706. 4:51:55This is going to be like the pillar upon which  everything else rests. And maybe it'll just be I
  3707. 4:51:59don't know like a blog post or something or maybe  like a video URL, right? And then what I want is
  3708. 4:52:04I want this to be able to create content for a  platform like X. I wanted to be able to create
  3709. 4:52:09content for a platform like LinkedIn. I wanted to  create content for Instagram. I wanted to create,
  3710. 4:52:16I don't know, scripts, maybe like long form  scripts. And then I also want short form scripts,
  3711. 4:52:23right? So we could do stuff. And then like  eventually, and I'm not going to get to this now,
  3712. 4:52:27I don't think, cuz it's kind of a big ask, but um  we should also be able to create like video like
  3713. 4:52:32full stack end video. Um that would be my that  would be my end goal. So, this is basically what
  3714. 4:52:38I want the app to do. I want you to be able to  provide one piece of content and then immediately
  3715. 4:52:42just like, you know, creates high-quality content  that's specific to each platform. And obviously,
  3716. 4:52:47we're going to need to do this through some  sort of dashboard. In addition, okay, I don't
  3717. 4:52:51just want this to be basic where we had like our  little dashboard on the left hand side with like,
  3718. 4:52:55you know, three things and then we have some other  like central section um over here. I want this to
  3719. 4:53:00be more interactive and I want this to have some  sort of like really detailed onboarding as well.
  3720. 4:53:05Um, this is naturally going to involve like a  fair amount if you think about it. Not only are we
  3721. 4:53:10going to have to do everything we did in the last  app, which was to uh summarize a landing page,
  3722. 4:53:15Stripe payment integrations, um, OD DB, some sort  of API wrapping, and then like a good way to,
  3723. 4:53:21you know, present that to the user. We're going  to have to go further because it's now not just
  3724. 4:53:24one like API that we're wrapping around, but  it's realistically going to be multiple. And
  3725. 4:53:28then we're also going to use our own custom logic  sort of um on-site logic to well not on-site sorry
  3726. 4:53:34but like our own proprietary stuff to do things  like manage the tone of voice the prompts and so
  3727. 4:53:39on and so forth. And perhaps one of the coolest  parts of this is I think the last app used AI as
  3728. 4:53:43just like an like an afterthought to help generate  you know a list of filters in this AI is going to
  3729. 4:53:48be like the main deal and uh hopefully we all  know like AI is the big thing right now. So,
  3730. 4:53:53it allows us to sell both uh AI and our value  props, but also AI through the apps. And my my
  3731. 4:53:58goal when building apps is I just want to  build stuff that like I actually would use
  3732. 4:54:01uh if I wouldn't actually use it as somebody in  a space. Odds are I probably don't understand the
  3733. 4:54:06problem enough to even be building this app in  the first place. But yeah, you know, if I could
  3734. 4:54:09save myself a bunch of time with this, that's  going to be a solid win. And then if I could
  3735. 4:54:12save other people time of that and stuff like  this as well, then that'd be even better. Okay,
  3736. 4:54:16so the very first thing I'm going to do is I keep  turning back to this 16 or 17-year-old kid. No,
  3737. 4:54:21he's 16 years old. His name's Leon. And what he's  been doing recently is he's been building like
  3738. 4:54:24really cracked high-quality landing page designs  for Gemini. And so he comes up with these very
  3739. 4:54:29very in-depth prompts. And then he ends up with  like a literal interactive app that you can like
  3740. 4:54:33move your your fingers around. Unfortunately, you  didn't take a video of this, but this is like,
  3741. 4:54:37you know, an app that there's like little strings  that are basically here being um processed every
  3742. 4:54:42second through I don't know if it's like web web  GUI or something like that, but it's some sort of
  3743. 4:54:463D library. And um he shares his prompts online.  He's really cool. I used him in my last video.
  3744. 4:54:50I wish I had half that uh brain at 16 years old.  And so what I'm doing just to start us off is I'm
  3745. 4:54:55going to copy this prompt that he's put together.  Okay? And then I'm just going to ask Gemini to
  3746. 4:54:59make me a landing page. And I just want it to  make me a landing page first before I do the rest
  3747. 4:55:03of the app because I just don't trust that it'll  be able to do both the very in-depth programming
  3748. 4:55:07required to build some sort of cool 3D generative  thing and then also do the app. So basically what
  3749. 4:55:12I'm going to do is I'm going to have it like  generate the the landing page and then we'll
  3750. 4:55:14build the rest of the app out afterwards. Um, so  you know, kind of non-traditional, but basically
  3751. 4:55:19what I've done here is I've just pasted all this  stuff in. Okay, I'm going to press enter. And I'm
  3752. 4:55:23not going to read this whole prompt to you, but  this is basically, you know, act as an elite,
  3753. 4:55:27award-winning creative developer and digital  generative artist. Your task to write a single
  3754. 4:55:30self-contained executable file that renders an  ultradetailed pixel perfect and breathtaking hero
  3755. 4:55:34section for a next generation tech company.  Critical constraints, do all this fun stuff.
  3756. 4:55:38Here's the theme and the content. You know,  provide some information about what I want and
  3757. 4:55:42stuff. And stylistically once we have this set up  um you know I'll make some minor modifications to
  3758. 4:55:46it so it's not a one to one clone or rip of this  uh and then we can actually move on with the app.
  3759. 4:55:52Now while I'm doing that just to save on time I'm  going to voice dump everything that I think this
  3760. 4:55:57app is going to include. Um and then I'm going to  send it over to claude code so that I can have two
  3761. 4:56:01of these instances operating simultaneously.  One that's probably a little bit better at
  3762. 4:56:05architecture design than the other that you know  is better at the front-end design that I'm asking
  3763. 4:56:08for. So, uh, I'm not going to repeat it all over  to you guys, but a I want to design an application
  3764. 4:56:15that takes a single piece of pillar content and  then immediately rewrites it, regenerates it,
  3765. 4:56:20and recreates it, and then syndicates it across a  variety of platforms. Okay? And I just gave that
  3766. 4:56:24over to Claude Code, and I asked it for a spec,  which is basically a highlevel description or
  3767. 4:56:29overview of what this app would look like. And I  just want to run you guys through this here while
  3768. 4:56:33Gemini is designing the actual generative part.  So this includes tech stack um app architecture
  3769. 4:56:39some info on the database schema some info  about the landing page and marketing site.
  3770. 4:56:42So after we're done with this, we'll use this  to modify it. Pricing and Stripe integration,
  3771. 4:56:46authentication and signup flow, onboarding  flow, the actual content syndication engine,
  3772. 4:56:51uh info about the dashboard, the content library,  AI configuration and voice model, scheduling and
  3773. 4:56:56calendar, analytics and reporting, settings and  account management, API and webbook architecture,
  3774. 4:56:59and then also some direct platform publishing  and then AI video generation stuff in the future,
  3775. 4:57:04which basically we're just going to like add stubs  or little nuggets that we could use to build that
  3776. 4:57:08out later if necessary. I've then given it some  information on the text stack and then asked it to
  3777. 4:57:13come up with some other things. So for instance,  we're going to use Next.js15. We'll use Tailwind
  3778. 4:57:17CSS plus the Shad CN/ UI component library. We'll  have Superbase Realtime for live updates. We'll
  3779. 4:57:23we'll do a bunch of other stuff as well. ZOD  validation. This is important for security cuz
  3780. 4:57:27I asked it to make sure that it was as secure as  possible on the first shot. What I'm going to do
  3781. 4:57:30is I'm just going to modify a couple of the pages  here. I'm probably not going to use a calendar.
  3782. 4:57:34Okay. Analytics look good. Um platform connections  for now. I'm just going to leave those out.
  3783. 4:57:38Um, AI voice prompt configuration is good. So,  I like this. This is like your tone of voice.
  3784. 4:57:44Just make sure that gets that in right. And then  settings, account, billing, and team. All that
  3785. 4:57:47stuff looks good. Here's like the data objects.  I don't want to spend too much time on that,
  3786. 4:57:51so I'm not going to worry about it. Um, that  looks solid. On the right hand side, it looks like
  3787. 4:57:55this generative component has now been done. So,  that's pretty sexy. Now, it's going to go design
  3788. 4:58:00the rest of the website. While we're looking  here on the lefth hand side from cloud codes,
  3789. 4:58:04uh we have a bunch of different feature sections.  The landing page pricing and stripe integration
  3790. 4:58:08is going to start at 19 a month or 190 a year. So  it's going to be 10 months basically giving two
  3791. 4:58:12free months to people. Of note, just before we do  this, the input method is really clean. Um I asked
  3792. 4:58:16it to be able to either paste raw content. So just  copy and paste a blog post, article, a transcript,
  3793. 4:58:21or a series of notes, or paste a URL. And the  whole idea is, you know, if we paste a URL,
  3794. 4:58:26um it's going to go through and then scrape the  whole website for us. So we didn't even have to
  3795. 4:58:30touch any of that. Um, additionally, I want to  be able to do things like paste a YouTube video,
  3796. 4:58:33although I think right now I'm probably going  to leave that out just uh as the demo. And then
  3797. 4:58:37once I have those core functions and features  in, then I'm going to do more. But you should
  3798. 4:58:41also be able to upload things like MP3s, waves,  M4As, OGs. Um, all these things should be auto
  3799. 4:58:46transcribed. And the idea is it's just going to  be like your one-stop shop portal for like, hey,
  3800. 4:58:50I just produced a piece of content. I'm going to  plug this in and then I'm going to have copy and
  3801. 4:58:53pasteable ready content to distribute to all these  different platforms with minor adjustments. And
  3802. 4:58:57obviously, I'll also be able to like change the  prompt anytime I want. Um, so very valuable for
  3803. 4:59:01me. Hopefully it'll be as valuable uh for other  people as well. Okay, very satisfied with the
  3804. 4:59:06first iteration of this landing page. As you see  here, there are some issues with this WebGL stuff,
  3805. 4:59:10but these are real particles that are being  rendered um in real time. Um I don't like how this
  3806. 4:59:14neurallex stuff is all over the place. Obviously,  that's that's okay. I've since told it to slow
  3807. 4:59:18things down a little bit, but yeah, I mean like  the text on the left hand side of the page looks
  3808. 4:59:22really really clean. Obviously, we have like nice  little mouseover buttons and and stuff like that.
  3809. 4:59:26Um, I'm going to change all of this signap  stuff to uh Splinter, but for now, I mean,
  3810. 4:59:30Gemini uh 3.1 and you know, prompts from Mr. Leon  Lynn over here are absolutely crushing it. So,
  3811. 4:59:36pretty stoked and looking forward where and  looking forward to where the next uh step
  3812. 4:59:40goes. After the next round of edits, we've also  added some additional sections. Common questions,
  3813. 4:59:44ready to syndicate, and then finally down here,  um, a full- length footer. So, that's looking
  3814. 4:59:48pretty sexy. The lines here are still moving  around a fair amount. So, I'm just going to modify
  3815. 4:59:51them a little bit more. But, we've now implemented  some sort of like mouse um interactivity. Do you
  3816. 4:59:56see how this thing is kind of like moving away  from my mouse as I move around the screen? So,
  3817. 5:00:00I can technically control this. It's just  it's not super uh what's the term? Trivial
  3818. 5:00:04or obvious to me as a user of the app how this  works. I've also had it change these lines. So,
  3819. 5:00:09that's going to slow down pretty significantly.  And then we can see what the final product looks
  3820. 5:00:12like. While I was waiting, I also had it go do  a little bit of research on other platforms. So,
  3821. 5:00:17Repurpose.io lately, Constant Studio, Buffer,  and so on and so forth. And then why Splinter
  3822. 5:00:22will solve it. So most are distribution only or  creation only. Splinter will do both. Basically,
  3823. 5:00:27it'll allow you to both create content and then  distribute it quickly. Um voice and tone being
  3824. 5:00:32an afterthought here. We're going to fix that  via um some pretty strong prompt engineering. I
  3825. 5:00:36think most people that are designing these sorts  of repurposing apps are more software engineers
  3826. 5:00:39than they are prompt engineers. I would consider  myself much more prompt engineer than a software
  3827. 5:00:43engineer. So that should allow us to get like  very high quality tone. Okay, these particles
  3828. 5:00:47are looking a lot better. They now move according  to my mouse, which is cool. And then these little
  3829. 5:00:52um things are no longer facing the opposite  direction. I'd say they're probably a little
  3830. 5:00:56too many of them. So, I think I'm going to remove  the entanglement ratio here just so we have three.
  3831. 5:01:00And then I'll probably also just adjust the color  of the particles a bit. So, you know, it's I don't
  3832. 5:01:05know, like kind of lightish yellow, maybe goldish,  something like that. Also see if maybe I can make
  3833. 5:01:10the particles just a little bit bigger. Right  now, I feel like they're kind of compressed,
  3834. 5:01:13which I'm not a fan of. still is kind of neat just  seeing this little streaming animation. Pretty
  3835. 5:01:17interesting seeing the logic and kind of the math  that uh ended up aggregating all these things
  3836. 5:01:23together. I mean, I'm just moving my mouse around  and there's clearly a deep relationship here,
  3837. 5:01:27but I can't exactly figure it out. I think that's  because they're modeling this in 3D instead of 2D.
  3838. 5:01:32Becomes a lot simpler when you see them in black  like this. There's definitely some 3D going on
  3839. 5:01:37here as we could see. And honestly, I think I like  the black. Um I like the 3D translation. So, I'm
  3840. 5:01:42just going to keep it at that. All right, awesome.  So, now that we're done with this, um, now I'm
  3841. 5:01:46just going to modify the content on this page. And  I'm just going to do it by giving Gemini the rest
  3842. 5:01:50of the instructions and saying go for it. Um, you  know, we're going to want to clean out some of the
  3843. 5:01:54contacts and stuff. Uh, but I'll show you guys  what that looks like. So, I'm going to say to
  3844. 5:01:58adjust the copy on the page to match the purpose  of the app, which you can find in this side of
  3845. 5:02:01this spec. I'm not actually going to like manually  do any of this. And then it'll go through and then
  3846. 5:02:06just adjust the rest of it. And yeah, I didn't  actually realize, but this is this is definitely
  3847. 5:02:10like a portal that we are moving through in 3D  space. So, it's actually more complex than I
  3848. 5:02:15thought it was. Looks clean to me. We now have  everything here set up. All of the syndication
  3849. 5:02:21text is in now. Um, it's still saying synapse,  which is kind of annoying. I don't think it got to
  3850. 5:02:25that. Cool. Good to go. So, let's build the rest  of the app now. Um, for us, it's going to be as
  3851. 5:02:29simple as just sending all of this information  over to Gemini and saying, "Excellent work.
  3852. 5:02:35I'd now like you to build the rest of the app  as detailed in splinter_spec.md. But there's one
  3853. 5:02:43change. I'm going to say along the way document  each update in an updates.md file so that we have
  3854. 5:02:50a history of tracked changes in case something  occurs or I need to feed this into another version
  3855. 5:02:59of the model of Gemini. And the reason I'm doing  this is because this is a pretty crazy long app,
  3856. 5:03:06right? There's a fair amount that's going on here.  Um, I anticipate I'm probably going to run out of
  3857. 5:03:09tokens at some point because I ran out of tokens  about an hour and a half into the development of
  3858. 5:03:13most apps so far. What I want is I basically just  want like a list of everything that it has done
  3859. 5:03:18up until the time that it did not do the thing.  Um, and I'm just going to store it in a file that
  3860. 5:03:22I can then give to either another version of  Gemini later on or clawed Opus 4.6 or whatever
  3861. 5:03:27the freaking model I want. And in this way, this  is almost like a GitHub um repo before I get all
  3862. 5:03:32the pushing logic and stuff in. But it gets to  take advantage of AI summarization features. So
  3863. 5:03:36I'm not going to have to load the codebase every  single time. I want to like analyze and you know
  3864. 5:03:39see what the problem is. This section cracked me  up a ton because I don't know if you guys have
  3865. 5:03:44uh seen the draw the rest of the owl meme, but  basically it's like how to draw an owl. Draw some
  3866. 5:03:51circles. Draw the rest of the freaking owl. Um  I feel like we've just done this so far and it's
  3867. 5:03:57doing that. So, thank goodness for AI, huh? This  initial implementation plan is going to be heavily
  3868. 5:04:02modified since we're no longer just building  a one kind of uh file uh website. Instead,
  3869. 5:04:08we're going to be distributing some of the stuff  across big file structure. Here you can see that
  3870. 5:04:12it's also set at the updates.m MD, which is quite  nice. So, we're going to see technical decisions,
  3871. 5:04:16feature implementations, and significant changes  applied to the Splinter project. And my hope is by
  3872. 5:04:20doing it this way and then later on feeding this  to um you know claude I can have both of these
  3873. 5:04:25models both claude code uh sorry claude opus 4.6  and then gemini 3.1 pro high basically like debate
  3874. 5:04:31about which features are better which things  to keep and then which things to remove. Agent
  3875. 5:04:35teams in cloud code does a variation of this right  now where basically they have like a shared chat
  3876. 5:04:40file and then they chat back and forth. Um, this  updates to me is just a slightly more streamlined
  3877. 5:04:44version of doing that without me having to  waste $400 in tokens cuz boy does that agent
  3878. 5:04:48teams feature consume a lot of them. All right,  so it's built the MVP implementation plan. Just
  3879. 5:04:53taking a quick peek through this. This is going  to need everything here, which is fine. Hopefully,
  3880. 5:04:58we are very used to getting all those API keys  now. And yeah, we're going to initialize Nex.js
  3881. 5:05:03directly inside of this root directory. So,  it's going to do all of these steps here. Oh,
  3882. 5:05:07hold on. I see that it's not actually taking that  into account. I'll say initialize in the same um
  3883. 5:05:15folder as root hero.html will be our landing page.  Just want to make sure that's super clear. And in
  3884. 5:05:22this way I get to pause the outputs. I'm not going  to waste a bunch of usage on you know building it
  3885. 5:05:27out and so on and so forth. That's where taking  a peek especially initially at what um Gemini is
  3886. 5:05:33doing can be pretty valuable. I always liken this  to sort of like a trajectory sort of thing. Let's
  3887. 5:05:39say over here is um I don't know South America,  okay, on the left hand side and then over here
  3888. 5:05:45is the westmost coast of Africa and hypothetically  you are a boat trying to make it from one side to
  3889. 5:05:51the other. And so this is you, right? And then  your goal is you want to go over here. Well,
  3890. 5:05:55logically speaking as you are leaving the port on  the eastmost side of South America. Okay. Um there
  3891. 5:06:01are a lot of different directions you could go.  You go this way, you go that way, you go this way.
  3892. 5:06:06only a very small subset of these directions will  actually get you to your goal. Obviously, you're
  3893. 5:06:10going to need to go like here, right? And even  then, I'm a little bit off. And so, initially,
  3894. 5:06:15I guess what I'm trying to say is the direction  that you pick even in like the first kilometer
  3895. 5:06:20as a boat heading to to to sail is really really  important for determining the final placement of
  3896. 5:06:25the app. Um, even if I was like one tiny little  degree off, that could be the difference between
  3897. 5:06:30me making it directly on target and then I don't  know like a one degree difference or something
  3898. 5:06:34could be the difference between me making it to  city that's like 100 km away. And so I usually
  3899. 5:06:41like to be around here to steer the model and  then once it's sort of like in this territory
  3900. 5:06:46or whatever, you know, if it's like on track well  enough that I think it's like going to be okay,
  3901. 5:06:50then I don't really worry too much about that. Now  on the right hand side here you see that the error
  3902. 5:06:54um the agent actually ran into an error. This is  another reason why I like being around. This can
  3903. 5:06:58occur for a number of reasons. This could occur  for token issues. It could occur because I don't
  3904. 5:07:03know like the API is just out. It could occur for  rate limiting reasons or just because sometimes
  3905. 5:07:08um some of these packages don't actually interact  nicely with Gemini and then it kind of struggles
  3906. 5:07:11with the terminal. But yeah, I'm just going  to be around for the first couple minutes for
  3907. 5:07:14a build that this is this comprehensive because  I don't want it to like make a wrong assumption
  3908. 5:07:18and then build something completely different to  what I want and then later on I'm just going to
  3909. 5:07:22have to go back and and redo it all anyway. Okay,  you got the app right over here. So, it's looking
  3910. 5:07:26pretty sexy. If I click get started, we now can  sign in or sign up. So, I'm just going to pretend
  3911. 5:07:32that I've done all of that. Now, we have the  onboarding. So, initialize workspace. Cool. So,
  3912. 5:07:40this is like all the platforms that I'd want to  connect to. It's good. This is really interesting.
  3913. 5:07:45Formality index, humor coefficient. I like that,  but I think we're going to have to add some to it.
  3914. 5:07:50So, I'm just going to go back to the model and  then I'll say change voice profile to a default
  3915. 5:07:58um to an advanced advanced setting advanced let's  say button where I can modify the prompt directly.
  3916. 5:08:09That looks pretty cool. Dry run simulation.  Hey, what's going on? Execute run. This is
  3917. 5:08:17going to be like when it actually does its  thing. Cool. Also add a um an additional
  3918. 5:08:26step right after the dry run that shows the  output. I'll wire you up to Claude Opus 4.6.
  3919. 5:08:41So we can test this next. Okay, we're now going  to enter the dashboard. Okay, so this looks like
  3920. 5:08:46a pretty simple dashboard still. I do like  the style we have. We're going to build out,
  3921. 5:08:51you know, a generative interface. It says  over here. I'm probably going to want to
  3922. 5:08:54move this stuff a little bit over to the left.  I'm not seeing anything under generative engine,
  3923. 5:08:58voice profiles, platforms, or settings. So I  guess right now we have the onboarding all the
  3924. 5:09:02way up to the dashboard. So that's pretty cool.  Still, if I click log out, I go back here. Then
  3925. 5:09:06if I go back here then uh Okay, cool. So yeah, I  think I'm understanding where we're at with this.
  3926. 5:09:11Uh it's looking pretty clean and I'm glad that I  managed to do all that stuff with just a little
  3927. 5:09:15bit of prompting. We still have that cool little  3D thing, too, which is really nice. Okay, so next
  3928. 5:09:20up, I'm going to feed in these instructions and  then I think what I'm going to do is I'm going
  3929. 5:09:24to have it continue the initialization.  Um this is going to be tough. I mean,
  3930. 5:09:30I really like this. I really, really like this,  right? But this is going to be pretty tough. Uh,
  3931. 5:09:36I guess we could probably autogenerate a  prompt that includes some settings with this
  3932. 5:09:42for the sliders. We'll use this in a prompt  to fill variables like formality and humor.
  3933. 5:09:56And then this dry run simulation. We'll  execute the input. We should get a new
  3934. 5:10:01one here. Systems nominals.  Cool. Awesome. Okay, cool.
  3935. 5:10:05Let's also start building out the dashboard.  I'd like you to replicate the attached image
  3936. 5:10:15in terms of content. Now, I'm going to go to  dribble over here. I'm going to go dashboard
  3937. 5:10:24and let's see what we can do here. I want  something that's just like much higherend,
  3938. 5:10:28cleaner. I do like the squareer look. Um, to me  that just implies like a high-end brand. So, I'm
  3939. 5:10:33going to look for something that does have that  square look. Let's try filtering by new instead of
  3940. 5:10:38um popular. That way, maybe we can get things  that other people haven't built before. Okay,
  3941. 5:10:44this looks pretty clean. I like this.  Let's see if we could feed this in. Oh,
  3942. 5:10:48sorry. We need to copy this.  We can't just do that. Okay.
  3943. 5:10:52uh in terms of content and style except I  want you to stick to our pre-established
  3944. 5:11:02um square no border radius. That's the little  um smooth corners. I don't really like that.
  3945. 5:11:11I also want you to add significantly more  functionality as per the initial doc initial
  3946. 5:11:19splinter spec.md. And this is looking pretty  clean. There's an advanced settings feature
  3947. 5:11:26here now where we can actually change things which  is quite nice. I'll pretend I'm executing a run
  3948. 5:11:32running style transfer. Okay, great. Awesome. So,  this looks kind of silly. Not a fan of the design
  3949. 5:11:39for sure, but um you know, it's cool that it has  a lot of the stuff laid out. Interesting. Yeah,
  3950. 5:11:45this is like highly opinionated stuff clearly. Um  all right, so I think what we're probably going to
  3951. 5:11:49want to do is on the left hand side, we're still  going to want to have like a like a database,
  3952. 5:11:57sorry, database dashboard panel. Um we're not  going to want to mention the model. I do like
  3953. 5:12:02the system log. That part's cool. All right, cool.  Let me just give this some stream of consciousness
  3954. 5:12:06feedback. Hey, this looks cool, but it's quite  opinionated. I don't like the dark borders. I'd
  3955. 5:12:11like a higherend sort of Lux design internally  that still sticks to um very similar to the design
  3956. 5:12:18on the landing page. I'd like you to remove all  mentions of the specific models that we're using.
  3957. 5:12:23I want some sort of lefth hand side pane that I  could use to select different views. I really,
  3958. 5:12:28really like the system log. I like the  credit usage, the generation, source items,
  3959. 5:12:34active platforms. These are fine. replace recent  archives with a graph. That graph should go really
  3960. 5:12:39in-depth on the number of generations and which  platforms we've connected and stuff like that.
  3961. 5:12:43We also need the rest of the app. So, I need a way  to see specific and individual generations. I also
  3962. 5:12:50need a way to create a new syndication. Right now,  when I create when I click create new syndication,
  3963. 5:12:54it takes me back to the wizard. But I want this  to take me to a page where I can insert content
  3964. 5:13:00either using URL or MP3 file upload or video  upload or paste in a bunch of text and then it'll
  3965. 5:13:09do the syndication for me. Remember, we're just  dry running all this stuff for now. Uh I'm going
  3966. 5:13:13to include some API credentials for anthropic in  a second. So you could hook up the cloud opus 4.6
  3967. 5:13:19six integration and change the rest of the  language on the actual app side to reflect
  3968. 5:13:24like normal app usage. For instance, I don't like  the term disconnect. I don't like the matrix. Um
  3969. 5:13:30I don't like, you know, some of the other  language that you're using here. It seems a
  3970. 5:13:34little too tryhardy. Okay, after about 40 minutes  of development, we did run out of tokens. But
  3971. 5:13:38never fear, that's one of the reasons why we're  using two models and not just one. So what I've
  3972. 5:13:43done is I've exported our conversation history  and then that updates file. And now I'm just
  3973. 5:13:47uh doing next steps which in my case involves  feeding in the enthropic API key. So I'm going to
  3974. 5:13:51go and find the anthropic API key here. I'm going  to call this uh for splinter. Then I'm going to
  3975. 5:13:59copy it over right there. Okay. And then what I'm  going to do is I'll say let's wire up Claude Opus
  3976. 5:14:084.6. Test a bunch of prompts. Give me a few uh a  few dry run examples. And then I'll pick the ones
  3977. 5:14:17I like the most. Let's say test 10 prompts.  Give me a few dryr run examples of befores,
  3978. 5:14:24afters, and I'll pick the ones I like most  and we can integrate them. In general,
  3979. 5:14:28the design quality of Opus 4.6 will be a little  bit lower. So, just keep that in mind. However,
  3980. 5:14:33um there are some other trade-offs. You know,  it's a little bit faster and then addition to
  3981. 5:14:36being faster, I think architecturally, it tends  to make like a better functioning application. So,
  3982. 5:14:40that's why I frontloaded the design with Gemini.  And then after the design and stuff like that was
  3983. 5:14:45all wired up, I did all like the little scripting  or I'm doing all of the little scripting and
  3984. 5:14:48backend passes with um you know cloud opus 4.6.  This database is now set up. So I can head over
  3985. 5:14:56to let's do two things. Under authentication I  just want to go to sign in signin providers and
  3986. 5:15:02then I'll remove that little confirm email step  and then under project settings I'm going to go
  3987. 5:15:06to API keys just so that this has all of the keys  that it needs in order to you know do whatever it
  3988. 5:15:11wants. So I already gave it the publishable key.  We'll go um superbase secret API key and then I'll
  3989. 5:15:18paste that in as well. And the idea is now it has  everything that it needs in order to manage the
  3990. 5:15:22Superbase instance for me. I don't really need to  be involved in this process at all. And I'm doing
  3991. 5:15:26this while Claude is basically just running  a quick little test on the prompts. I'm just
  3992. 5:15:30going to pick the best prompt for now and then  I'll worry about like optimizing the hell out of
  3993. 5:15:33it later. Okay. And whereas anti-gravity was using  its own built-in browser, uh Claude Code typically
  3994. 5:15:38uses Chrome DevTools. So that's what it's doing  right now. jumping on taking a screenshot and then
  3995. 5:15:42it's seeing an internal server error. So whatever  it did either didn't compile or there was just
  3996. 5:15:46some problem on the back end. Um so that's what  it's fixing up now. As you can see the syndication
  3997. 5:15:51page here for create is much lower quality. Um  and as mentioned you know cloud is just nowhere
  3998. 5:15:56near as good as Gemini at least as of the time of  this recording and designing those really high-end
  3999. 5:16:00uh looks unless it's like per perfectly basically  trying to duplicate functionality which is
  4000. 5:16:05unfortunate. Um, it is going to make some minor  changes here because it it can't actually click
  4001. 5:16:09this generate button. So, it's cool that it  can kind of run that testing loop on its own,
  4002. 5:16:13but all of this is just in contrast with Gemini's  high quality design. And it looks like it created
  4003. 5:16:18a LinkedIn post and then also an X and Twitter  post. Just taking a peek here. It took us 3 years
  4004. 5:16:22to hit 1 mill AR with our SAS product. Here's what  actually moved the needle and what didn't. So,
  4005. 5:16:26this is a um phrase that I explicitly said that  I didn't want in the prompt. So, obviously,
  4006. 5:16:31I'm going to have to do some adjustment there. We  sell to dental practices only dental practices.
  4007. 5:16:35The temptation to go horizontal was constant,  but saying narrow am meant we could out build and
  4008. 5:16:38outmarket anyone in the space. We charge more than  felt comfortable from day one. Honestly, the price
  4009. 5:16:41anxiety never fully goes away, but underpricing  would have killed us. Okay, just while we have
  4010. 5:16:45this, I'm going to go back to the actual page.  Make sure that nothing else was changed here.
  4011. 5:16:50Cool. So, the design here is quite nice, right?  Hopefully, we can we can see that. The question
  4012. 5:16:54is where do we go from here? Get started. Sign up.  What's the wizard looking like? Okay. Okay. And
  4013. 5:17:04then we're going to have our prompt here. Try run  simulation. Sure. Oh, is this now actually using
  4014. 5:17:11real cloud code? No, it's not. Okay, cool. Uh,  sorry. Um, Opus 4.6. We'll sign off. Enter the
  4015. 5:17:17dashboard. So, the dashboard here is looking a lot  simpler. Um, you know, we we're missing a fair few
  4016. 5:17:24of those cool design features that we had before.  And then we also have little rounded corners which
  4017. 5:17:30I don't like. So, I'm just going to dump a bunch  of instruction into Claude and see if it can solve
  4018. 5:17:34this. Hey, I want the design of the dashboard to  reflect the design of the landing page. Right now,
  4019. 5:17:42there's a very big discord between the two.  Notably, the corners are rounded in the dashboard
  4020. 5:17:47and not rounded everywhere else. There's also  color discords. We're using this soft purple,
  4021. 5:17:52which uh is correlated with which is typically  associated rather with LLMs. I don't want pill
  4022. 5:17:57style things anywhere here. And in general, I want  you to use the same fonts in the landing page for
  4023. 5:18:03the new syndication or create page. I like how  we've laid this out so far with the URL, file,
  4024. 5:18:08or paste text, but rather than have three buttons  that the user has to click, I just want them to be
  4025. 5:18:13able to do it um do all of these simultaneously.  So, just have one field inside of that field
  4026. 5:18:18allow users to either paste text, import a URL, or  upload the file. It'll eliminate some complexity,
  4027. 5:18:24keep things really streamlined and simple. also  allow them to select which platforms they'd like
  4028. 5:18:28to syndicate content to at the bottom. Right now,  the generating for button, generating for section
  4029. 5:18:33rather, doesn't allow us to um make any of those  changes. Finally, make sure that the app looks
  4030. 5:18:38similar to the landing page. As mentioned, it's  very important that we get this one right. Oh,
  4031. 5:18:41this is much better. Okay, as we see here, we  now have that perfect design unification. I
  4032. 5:18:45like the new syndication button up top. Um content  library, votes, profiles, analytics, config, and
  4033. 5:18:50API access don't fully work yet, but this looks a  lot cleaner. So, we paste a URL. or drop a file or
  4034. 5:18:56type our content here. If I go into my finder, if  I go into my finder and drop it, does that work?
  4035. 5:19:02Oh my goodness, it does. That's really clean.  Likewise, if I paste a URL, so I don't know.
  4036. 5:19:08Let's do this one here. Okay, for my big claw code  course earlier and paste that in. Does that work?
  4037. 5:19:14URL detected. Really clean. Okay, we also have  blog x, Twitter. Okay. Okay, this is much much
  4038. 5:19:19nicer. Thank goodness. Um, obviously this is  going to be difficult to see the differences
  4039. 5:19:24between these lines. So, looks fantastic. Let's  add mild differences between the lines on the
  4040. 5:19:31generation throughput graph. I also want to build  out pages for content library, voice profiles,
  4041. 5:19:37analytics, setup, and API access. So, work all of  those out. Add uh whatever relevant features make
  4042. 5:19:43sense. And if there are any additional features  that you think would make sense on the lefth hand
  4043. 5:19:47side panel, please add them. I'm uh attempting to  increase the at least perceived sophistication of
  4044. 5:19:53the app right now. Okay, I actually just stepped  away to grab myself some breakfast and came back
  4045. 5:19:57and it looks like Claude is still monkeying away  at this. It's been probably 30 or so minutes.
  4046. 5:20:03I've had very little actual hands-on involvement  and uh yeah, you know, like the agentic workflow
  4047. 5:20:09time horizon of this specific model tends to be  quite large. Um, I'll say Gemini actually has
  4048. 5:20:14a slightly longer one, but when you prompt  it right, where essentially you say, "Hey,
  4049. 5:20:17here's a big road map of things. Here are a bunch  of changes that we've already made. Here's the
  4050. 5:20:22uh whole spec of the thing that we ultimately want  to build." And then you just let it run loose. It
  4051. 5:20:27can operate quite independently for quite a  long time. Um, and so this has gone through I
  4052. 5:20:31think three or four context windows at this point  considering it's about 200,000 or so tokens. You
  4053. 5:20:35know, I've spent a few million tokens um using the  cloud or anthropic API. That's multiplied by fast
  4054. 5:20:41mode here. This sort of approach isn't the best  for everybody because of costs, but in my case,
  4055. 5:20:45I'm happy to trade off that cost for um time  as previously and will continue to do. Checking
  4056. 5:20:50back in on the app, it's looking significantly  more fleshed out. We have a content library up
  4057. 5:20:55in here with the actual posts themselves. We can  go grab these posts and do something we wanted
  4058. 5:20:59to. There are voice profiles now. Um there is a  brand voice, casual, blog. You can adjust that
  4059. 5:21:06using this little section down below. You can also  add writing samples for best results which will
  4060. 5:21:11improve the probability that an AI model actually  outputs what it is that you want. Generation
  4061. 5:21:15volume right over here along with tokens used,  average numbers per session, platform breakdown,
  4062. 5:21:19everything that I basically like talked about  in the spec. Finally, automation rules. So,
  4063. 5:21:24um this is like a workflow thing where you can  automatically syndicate new content. Basically,
  4064. 5:21:27every time you add new content, it'll  automatically go through a big flow. We have
  4065. 5:21:31like enabled and and disabled and stuff like that.  Right now, these are all just stored on the local
  4066. 5:21:35database. um it's left to be seen essentially  whether or not I could scale that up. We have
  4067. 5:21:40profile platforms. This is where I can connect  and disconnect and so on and so forth. And ideally
  4068. 5:21:45this would open up a little like connection  panel. And then uh you know we have notifications
  4069. 5:21:49supposedly throughout email with the ability to  export all data. And this is really the section
  4070. 5:21:54that I'm I'm the most excited about because uh you  know if you make your apps like agent compatible
  4071. 5:22:00via API um I think that's going to be a massive  market later on. So, what I've done is I've added
  4072. 5:22:04an API access section with like supposed  production keys and stuff. This isn't fully
  4073. 5:22:08fleshed out, uh, as I'm sure you can imagine, but  still pretty reasonable. Um, what I'd like to do
  4074. 5:22:12next is basically want to verify that all this  functionality works and and actually like does
  4075. 5:22:17what it is that they imply that it does. And so  for this, I'm probably going to use a distributed
  4076. 5:22:23um cloud code either agent team or I'm just going  to ask it to run through one by one by one. The
  4077. 5:22:27idea would be, you know, spin up a se separate  instance to test the API key while you're spinning
  4078. 5:22:31up a separate instance to test the notifications  while you're spinning up a separate instance to
  4079. 5:22:35test the automation rules. We'll see how all  that stuff goes. Hey, this looks fantastic.
  4080. 5:22:38I don't think there's anything else here that I  really want on the app. Um, maybe on the dashboard
  4081. 5:22:43there is a little bit of white space at the bottom  because the system log is just just a little too
  4082. 5:22:48long compared to the connected destinations.  I think we could probably fix that by adding
  4083. 5:22:52one additional row of connected destinations.  That'll um match everything up quite nicely.
  4084. 5:22:56Everything else looks really great. My next desire  is to test this end to end every specific feature.
  4085. 5:23:02Just going through a really simple setup here  for LinkedIn O because I want to verify that
  4086. 5:23:06this actually works. So, uh, we're going to add a  couple products to the app. So, share on LinkedIn,
  4087. 5:23:12we have to do this. So, request access. We also  need, um, sign in with LinkedIn using open ID
  4088. 5:23:18connect. So, I'm going to request access to that  as well. And the good news is, you know, you don't
  4089. 5:23:21actually have to know how to do this yourself.  This is just stuff that uh in this case Claude,
  4090. 5:23:25but Gemini as well can just walk you through.  Then under OOTH 2.0 settings, we need to add this
  4091. 5:23:30redirect URL. So I'm going to go up to O. Just  going to grab the authorized redirect URLs. And
  4092. 5:23:36then I'm going to paste this in. And then I'm also  going to copy both the secret um into this ENV
  4093. 5:23:43file. And then I'm going to uh okay, added restart  dev server etc. And then when this is done,
  4094. 5:23:51I need to go to setup platforms. Connect LinkedIn.  Okay, cool. So, I'm now going to check out what's
  4095. 5:23:58going on over here. We'll mock. We go to setup  platforms and then connect LinkedIn. This is going
  4096. 5:24:06to open up a little LinkedIn dialogue. I'm then  going to sign in using my own credentials. Okay,
  4097. 5:24:11now I have a phone number that I have to verify.  So, I did just get this. I'll type that in.
  4098. 5:24:22Now I'm going to sign in as myself. Cool. And it  looks like LinkedIn status is now connected. I'm
  4099. 5:24:28going to head back over here and say connected  just fine. So we should be fine with this. Um
  4100. 5:24:35find some way to store all of that info so we  don't need to reconnect next time. All right.
  4101. 5:24:43So, we just did this um you know with with  LinkedIn. So, I should be able to go to new
  4102. 5:24:49syndication now and then I don't know. Let me just  like find an actual post that I made before. Maybe
  4103. 5:24:53my my blog. It's a good source for this stuff.  What's a fast one right over here? Actually, let's
  4104. 5:25:00test this functionality. We'll click generate. I  don't know if it's actually feeding in this. So,
  4105. 5:25:07that'll be the tough thing, the thing to double  check. We are on a generating tab. It's a fair
  4106. 5:25:12amount of content. So, you know, I'm not expecting  it to finish basically immediately. Oh, also we're
  4107. 5:25:16syndicating to LinkedIn supposedly. We should have  like a final check before we actually publish it.
  4108. 5:25:22Okay. Okay, cool. So, it's double checked to  basically see whether or not we're connected.
  4109. 5:25:26And so, X doesn't have publish, but LinkedIn does.  Most business small business owners are terrible
  4110. 5:25:30at hiring. Honestly, it's not because they're bad  at business because nobody teaches you how to do
  4111. 5:25:33it properly. Biggest mistake, hiring based on gut  feeling instead of actual data. You meet someone,
  4112. 5:25:36they seem sharp. Cool, cool, cool. All right. Uh,  we still have some issues here. So like I don't
  4113. 5:25:41know hashtags. Nobody uses hashtags anymore,  buddy. Remove that. Explicitly add it to the
  4114. 5:25:48prompt. Uh we should never generate any sort of  hashtags. Also, I'd recommend against emojis in
  4115. 5:25:53general. And then let me see what are we doing  that is sort of unfortunate. Most small business
  4116. 5:25:58owners are terrible at hiring. And honestly, it's  not because they're bad, but it's the biggest
  4117. 5:26:01mistake. Okay, so we have to avoid um LLM isms.  Like essentially the main LLM writing pattern
  4118. 5:26:10that pushes it into uncanny valley territory is  when you jump between extremely short sentence
  4119. 5:26:16lengths and then long sentence lengths and then  do that over and over and over again. That's not
  4120. 5:26:20how most human beings will write unless they're  trying to be direct response copyriters. And for
  4121. 5:26:25the most part we are we are not. So find a way to  adjust the prompt. Cool. And then everything else
  4122. 5:26:29looks pretty good. So I should be able to actually  like push this. Um, thing is I don't really want
  4123. 5:26:34to because then I'm going to have to publish this  on my own LinkedIn, right? Ah, I guess we're going
  4124. 5:26:38to have to test it. All right, why don't we go to  another page here and then just verify whether or
  4125. 5:26:45not this is being published to LinkedIn around  personal profile. If it is my personal profile,
  4126. 5:26:49I'm just going to delete it basically immediately  because I don't want all my all my fans to see
  4127. 5:26:54that. How do I do this again? Good god, man. Okay,  here we go. And we should be able to right click,
  4128. 5:27:00press delete post, right? Okay, cool. Okay, just  ran into one issue right before I did this. So,
  4129. 5:27:06I'm just going to Oops, that's not what I wanted  to paste. Um, I wanted to paste this. There
  4130. 5:27:11you go. So, we ran into a problem just as I was  about to do this. I I don't know if it like out
  4131. 5:27:17um just ran out and sort of timed out or  something, but okay. There we go. There we
  4132. 5:27:20go. That's better. Okay. And now we should be able  to go to dashboard. I would hope anyway. Okay. It
  4133. 5:27:27is going to force me to do this signin flow. We  do have some more platforms here as you could
  4134. 5:27:32see. Fix the onboarding wizard as well. It should  now um function off of live data. Right now it's
  4135. 5:27:36just doing the basic pass with templated stuff.  Okay. Setup. All right. All right. Here we go.
  4136. 5:27:43Content library. Go back to new syndication here.  Go drive blog. Why don't we get something maybe a
  4137. 5:27:48little bit shorter like this. Paste that in. Click  generate. We'll exit out of X Twitter so that we
  4138. 5:27:54only have the syndication option for my LinkedIn.  Then we will go to my LinkedIn and then see if we
  4139. 5:27:59could actually publish this. This is a blog post  I wrote basically all about interacting with my
  4140. 5:28:04YouTube comments. I said uh you know the statues  that we are building aka our YouTube comments last
  4141. 5:28:11way longer than the statues that people throughout  history have built because we don't know if people
  4142. 5:28:16are going to be looking at these comments in  the year 2148 and the year 20,048 or what.
  4143. 5:28:20So there's a lot of potential life there. Okay.  Clicked publish. Refreshing. Not seeing a post,
  4144. 5:28:27which is good. I just clicked publish.  I'm not seeing a post on the LinkedIn. Uh,
  4145. 5:28:34let me just on the generated content. Really helps  to be hyper specific. Did this copy work? Yeah,
  4146. 5:28:45the copy worked. Okay. So, just want to double  check. Going to refresh this. And then I'm also
  4147. 5:28:51going to head over to left click and see maybe if  we published it to there instead. I should be able
  4148. 5:28:56to pull this up just by going back to the LinkedIn  page. Four left clicks. So, I can click on that.
  4149. 5:29:01Go back to the company page and then we'll go  page posts. Okay. I'm not seeing a page post here,
  4150. 5:29:06which is nice. Oh, wow. 675 followers. Did not  have any idea 675 followers in that company page.
  4151. 5:29:12That's funny. Looks like there was a specific  issue with how we pushed this, which is okay. So,
  4152. 5:29:16we're going to use actual API generate calls now.  And then I have the post right over here. Just
  4153. 5:29:20going to head right over here. Click publish. Not  seeing any sort of notification. That's an issue.
  4154. 5:29:25So, I'll head back to Cloud Code. I'm not seeing  any sort of notification after I click publish.
  4155. 5:29:29Honestly, the experience doesn't feel very  snappy to me. I think the cursor might also be
  4156. 5:29:34uh reason why. Find a way to just improve the  perceived customer experience when they click
  4157. 5:29:39that button. Whatever it is, toast, menus, and  whatnot. We'll go back here. I'm just going to
  4158. 5:29:45quadruple check. Make sure I didn't. Did I post?  No, I haven't posted. And then I'll do the same
  4159. 5:29:50thing for leftclick. Let's go leftclick LinkedIn.  Just double check that that didn't post to either.
  4160. 5:29:57It might have. Just unsure if I'm posting to  company pages right now or my own. Okay, doesn't
  4161. 5:30:02look like I'm posting to either. One thing I'm  seeing here is we actually have been storing these
  4162. 5:30:06in the database now, which is cool. Um, our local  database to be clear, but still a database. And
  4163. 5:30:10so, you know, we can copy this. We could post this  to LinkedIn and whatnot if we wanted to manually.
  4164. 5:30:15Um, but I do want to check to see whether or not  we could post u specifically like uh, you know,
  4165. 5:30:20using that flow that we we showed you earlier.  So, I'll go back to new syndication. We're just
  4166. 5:30:24going to do one more. Okay. Yep, we got it. I  got to delete the hell out of this thing ASAP,
  4167. 5:30:29please. Thank you. And uh yeah, we've just  verified that this actually does post. So,
  4168. 5:30:33fantastic work. That's incredible. Um, super  cool. Super cool. I'm going to go back here. Hey,
  4169. 5:30:38I tried publishing and the first time I clicked  it, nothing happened. I waited five more seconds
  4170. 5:30:43and then I clicked it again and that time it  went through the whole publishing loop and
  4171. 5:30:46it actually appeared on my LinkedIn. Diagnose why  this might be the case. Go ahead and fix. Another
  4172. 5:30:51cool feature is in the top rightand corner we  have a new. So I can actually just click new,
  4173. 5:30:54go back here and then do another one. Um and  then I can also store all of that as you guys
  4174. 5:30:59saw before inside of the content library along  with the specific generation for that um rung. So
  4175. 5:31:05that to me is really really neat. Also the fact  that we have sort of the ability to go listical
  4176. 5:31:09view is cool. You can tell that this really ran  with the spec that I gave it and it's um it's done
  4177. 5:31:14a good job. I don't know. Okay, cool. Yeah, even  the search works. So very high quality stuff here.
  4178. 5:31:19I'm going to head over to voice profile and see if  I could maybe set this as the default casual blog,
  4179. 5:31:24do some editing and just double check what's  going on. So, as you can see, we can select
  4180. 5:31:28these here. Um, I don't know. Is there any way  to like go deeper into what the actual prompt is,
  4181. 5:31:32though? I'm not seeing that. I'm just seeing  like the ability to calibrate formality, humor,
  4182. 5:31:36and emoji usage. So, I think I'm going to have  to add that feature. Hey, under voice profiles,
  4183. 5:31:40I'm noticing that we can calibrate formality,  humor, and emoji usage, but I don't see any way to
  4184. 5:31:45adjust the actual prompt itself. What I want you  to do is to add just like we have in the wizard
  4185. 5:31:50some sort of advanced drop down that I can click  on that allow people to actually modify the uh the
  4186. 5:31:54underlying text as well. Under analytics, I want  you to make sure that we are actually reflecting
  4187. 5:31:59real analytics. Uh right now I'm not sure if we're  pulling from our database or what's going on. I do
  4188. 5:32:05see that the recent activity here is updated with  the LinkedIn post, which is pretty solid, but I
  4189. 5:32:09want to make sure that everything else is good,  too. Finally, under scheduling, um verify and
  4190. 5:32:13test that this works for LinkedIn. It looks like  we have a scheduled post coming up. That said, I
  4191. 5:32:17don't want you to actually publish it on LinkedIn.  Um, I just want you to verify that everything
  4192. 5:32:21works up until that point. I've now been given  this initial schema. What I'm going to do is I'll
  4193. 5:32:25head back to Superbase, go to the SQL editor, and  paste this in. Just verifying that these comments
  4194. 5:32:29work. Okay, it looks like they do. I'm now going  to hold command and press enter. We're going to
  4195. 5:32:33run this. And we see success. No rows return. I'm  going to go back to Cloud Code. And it looks like
  4196. 5:32:38my Gemini subscription is finally coming back. The  rate limiting said it would be 1228. So, we have
  4197. 5:32:45just another 10 minutes here before I can get  back to that. Um, which I think I'm going to do
  4198. 5:32:48for like a final design. But that should allow us  to push through probably most of like the database
  4199. 5:32:53migrations and stuff. Superbase SQL added. You  know, just to be clear, I don't like combining
  4200. 5:32:59multiple um different models like while I'm in  the middle of a development session because I
  4201. 5:33:03like all of the context that Cloud Code has to be  used in the cloud code thread and all the context
  4202. 5:33:07of Gemini has to be used in the Gemini thread.  generally speaking, you get much higher quality
  4203. 5:33:11results because uh this thing has processed so  many tokens at this point. You know, has so many
  4204. 5:33:15so much history of like past design decisions and  stuff like that that it just inherently gets what
  4205. 5:33:19it is that I'm trying to say. If I were to try and  just have Gemini, hey, pick up where whatever left
  4206. 5:33:23off, you would basically have to do the entire  job of retraversing all of those failed paths. So,
  4207. 5:33:28we're going to push this through with cloud code  and then at the end I'll probably do like a little
  4208. 5:33:31design or redesign. Um maybe do some finishing  touches, some some final polishing with Gemini.
  4209. 5:33:36Okay, so I'm going to say let's go 100% superbase  and we should be good. And it just got back to
  4210. 5:33:40me saying that the superbase migration is now  complete. So it's also given me a summary with a
  4211. 5:33:44bunch of API route os. It's verified the build and  whatnot. Verifying the build to me is not enough.
  4212. 5:33:50I need to actually go through the whole testing  um end to end. So I'm going to have it log in,
  4213. 5:33:54put in some credentials, and actually like do said  testing on its own because it has the ability to
  4214. 5:33:58screenshot things and whatnot. Then once all this  stuff is done, it's just a matter of pushing that
  4215. 5:34:03to um you know actually like a like a like  a Netlefi host and then also adding payments
  4216. 5:34:07and stuff like that. The reason why I'm not adding  payments right now is uh I sort of had a change of
  4217. 5:34:11heart. I thought a little bit about um what would  Stripe require in order to set all this up and I
  4218. 5:34:16think Stripe would work better with like a live  published app since uh it has like a fair amount
  4219. 5:34:20of callback functionality and I want to be able to  give it a URL. So I I'll do all that stuff after.
  4220. 5:34:24Anyway, I'm not touching anything here. Model is  now proceeding autonomously and it's doing set
  4221. 5:34:28testing without me. spotted a couple of issues  so far with the voice profiles table. So, it's
  4222. 5:34:32going to go through and then actually apply the  migration. I can see this doing a bunch of silly
  4223. 5:34:37BS here trying to solve some Superbase issue. So,  I told it just to give me whatever uh it needs
  4224. 5:34:42and I'm going to go through and actually I can see  this doing some silly BS issue. Um what I'm going
  4225. 5:34:46to do is I'm just going to run this directly  in the Superbase editor instead. It's saying
  4226. 5:34:50alternative install this via Homebrew to run it  from here. I mean, like it can, but I don't know.
  4227. 5:34:54I don't really want it to waste my damn time or my  tokens. So, I just created it. Um, should be good.
  4228. 5:35:03Cool. Yeah. And you can see I've already done the  creation. So, we've saved ourselves some tokens
  4229. 5:35:07there. I would hope. And uh yeah, I mean like  that's why I keep an eye on it. Good mental model
  4230. 5:35:11here is pretend you're at like uh some security  desk job and part of your job is just like
  4231. 5:35:16reviewing CCTV footage and there's like 10 CCTV  things in front of you. You're just like kind of
  4232. 5:35:19glancing around at each. It's basically what we're  doing here. Although um you know with a little
  4233. 5:35:23bit less context switching since I'm using fast  mode. But everything that I've done here, you can
  4234. 5:35:26absolutely replicate with like two or three cloud  windows open. The reason why I'm starting with
  4235. 5:35:30GitHub first is because I want this to be version  controlled. And to be honest, like you could have
  4236. 5:35:35done this from step one. I just uh I'm not working  with anybody else in this project. It's just me,
  4237. 5:35:40myself, and I. So this local folder is enough  for me until I get to, you know, the part where
  4238. 5:35:44I'm ready to go. You can see it's um looking to  ask a question. Uh h I should probably do this
  4239. 5:35:49privately because I don't want anybody to take  my tokens. Cool. We'll do that after it's done.
  4240. 5:35:56um push to Netlefi. Use my credentials  since we're just demoing. I'll remove
  4241. 5:36:02them later. And that way I'm going to  have like my env keys and stuff like
  4242. 5:36:05that so I can actually go through the  uh the generation process and stuff.
  4243. 5:36:11Cool. So now it's setting up Netlefi  deployment and then now we just need to
  4244. 5:36:15connect to Stripe. So I'm going to head back  to Stripe and then I'm going to open up that
  4245. 5:36:19uh publishable key thing. So signing in should  now open up a sandbox. So what I can do is I can
  4246. 5:36:25actually copy the publishable key. Oh, that's not  it. I'll head over to ENV and then I'll also say
  4247. 5:36:32Stripe publishable key. Add that. Also go Stripe  secret key. I'll add that. And I realize it's
  4248. 5:36:40probably going to have to redo the update. Hey,  just a heads up. I've added Stripe publishable
  4249. 5:36:44and secret keys tov as well. Our next step is  going to be to connect it to Stripe to get our
  4250. 5:36:49payment integration set up. I'd like you to handle  this end to end autonomously. Once it's done,
  4251. 5:36:55um, I'll do an endto-end test of the app myself  and let you know if there's any final changes.
  4252. 5:36:59Cool. So, we've since pushed this app live and we  can actually see it at splinter-app.netlifi.app. I
  4253. 5:37:05don't really think I needed that dash app there,  but the model made that choice and that's okay.
  4254. 5:37:09Um, I'm liking this. It also looks like we have  that nice little I didn't really notice, but we
  4255. 5:37:13have that nice little 3D geometric background.  Um, we're going to have to find ways to insert
  4256. 5:37:19these pipeline visualizations. I've realized now  that we haven't done that on the landing page,
  4257. 5:37:22but it shouldn't be too hard. I think we'll be  able to sort that out pretty quick. I'm also
  4258. 5:37:26going to want to widen the landing page a little  bit because notice how the hero header is really
  4259. 5:37:29wide and then everything else is really kind of  compressed. So, I'm just going to voice dump this
  4260. 5:37:32and then um have it run through some final  designs. Hey, the landing page looks solid.
  4261. 5:37:38Just checking the live Netifi link. Now, I'd like  you to add more platforms and social proof. Um,
  4262. 5:37:43so just add more company logos and stuff. Aside  from the hero header, I find that everything
  4263. 5:37:48underneath is pretty squished. Like it's not  very wide. It's very narrow. So I'd like you
  4264. 5:37:51to significantly widen the design. Also, we have  processing pipeline visualization, tone analysis,
  4265. 5:37:56matrix, multi format, compiler. These three are  placeholders that were meant to be filled in.
  4266. 5:38:01What I'd like you to do is actually go through our  app and then fill this in with relevant sections.
  4267. 5:38:06um not screenshots, but actually just mini builds  that uh elucidate various parts of the app,
  4268. 5:38:12whatever the the specific feature is. Make sure  to widen the pricing and then the call to action
  4269. 5:38:16as well. And just in general make this a little  bit longer and a little bit sexier. All right,
  4270. 5:38:21let's take a peek at that actual landing page now.  We should have everything essentially ready. Oh,
  4271. 5:38:27that is so cool. I don't think I'm going to get  over just how interesting it is to move my mouse
  4272. 5:38:32around. Um, looks like we added significantly more  context here. So, we could see these little steps.
  4273. 5:38:37And wow, that some of this is actually dynamic,  which is wild. So, future content creation isn't
  4274. 5:38:42about producing more. It's about distributing  smarter. Here's how we scale our reach 10x without
  4275. 5:38:46hiring a single additional writer. LinkedIn X,  blog, whatever. That's cool. We can then actually
  4276. 5:38:51move these things around. That's really, really  interesting. Oh, wow. Nice. So, we can move the
  4277. 5:38:58emoji usage and stuff like that around and then  add various features and and buttons. And this
  4278. 5:39:04over here has a bunch of different sections for  different types of formats. Hot take. If you're
  4279. 5:39:10still copy pasting the same content across every  platform, leaving 70% of your engagement on the
  4280. 5:39:13table. Hell yeah. Threads. We added some more  steps down here. So, clean. We then added some
  4281. 5:39:19data. We added an additional pricing tier,  which is nice. Creators love Splinter. So,
  4282. 5:39:23we have some supposed big creators. And then  we can start our free trial or book a demo. I
  4283. 5:39:27don't know if there is a demo feature though.  Is there? Yeah. Okay. So this is where we add
  4284. 5:39:30our calendar. It's pretty neat. I'm probably  not going to do the demo stuff. Um anyway,
  4285. 5:39:34that's fine. We'll start free trial. So now I'm  going to add some context. So we'll go Nikki
  4286. 5:39:40Sarif. Go [email protected]. Actually, why don't we  use a real email? We'll go a very simple password.
  4287. 5:39:51So the creating is now taking us to the  onboarding. This is super clean. So maybe we just
  4288. 5:39:57want LinkedIn for now. We're going to set up our  voice. So move this around. Looks like we don't
  4289. 5:40:03have access to that advanced section just yet.  Let me see if I could pull something from my blog.
  4290. 5:40:11Maybe we'll say this. Paste this in. Then I'll  click generate. We should go through a generation
  4291. 5:40:19script here and it should be real. Okay. So  the output is what you get in production. Nice.
  4292. 5:40:31Cool. This is now taking my post and then  it's um iterating on it slightly. Wow. This
  4293. 5:40:39is great. Nice. Oh, nice. Yeah. So I think  the the difference here and the reason why
  4294. 5:40:49this reads so well is because I specifically told  it do not have those crazy short sentences with
  4295. 5:40:56like super long sentences immediately after  and then alternating cuz it's like blah blah
  4296. 5:41:01blah blah blah blah blah that's not pattern  that's signal right it's like you know that
  4297. 5:41:05that's AI just the way that it writes it this  has solved that for me which is clean okay
  4298. 5:41:10nice anyway finish setup apparently we're  all set so we'll go to the dashboard here
  4299. 5:41:15okay And we ran into our first issue, which is an  application error. So I'm going to paste this in.
  4300. 5:41:22This occurred right after the onboarding wizard.  And now I'm just going to continuously push until
  4301. 5:41:28I get all the way through the app. Now,  logically, what we should do after we are
  4302. 5:41:31done our little onboarding wizard is we should  go directly to a pricing page. I'm okay with
  4303. 5:41:37people making like their initial request that  little LinkedIn rewrite thing without having
  4304. 5:41:41to sign in because while I know some people abuse  that um the abuseness I think will be outweighed
  4305. 5:41:46by the convenience and then the wow factor of  actually just being able to pump content in and
  4306. 5:41:50then getting it like nicely formatted and tuned  for LinkedIn. So I'm going to keep that in. But
  4307. 5:41:55immediately after like we do want to force them to  pay and at that point they'll be in a little bit
  4308. 5:41:59of like reciprocity like they will just have used  our app for free which allows us to say use for
  4309. 5:42:03free and then in return um you know it's sort of  like a like a teeter totter or a scale in return
  4310. 5:42:09they're going to want to balance that by paying  us and then I think I'm going to like make the
  4311. 5:42:13intro offer like pretty affordable so people can  you know sign up get the ball rolling and stuff
  4312. 5:42:18like that without necessarily having to spend  a lot and then um from there you know as they
  4313. 5:42:22go grow addicted to Splinter her then uh you know  eventually the monetization will improve. Okay,
  4314. 5:42:29this looks pretty good. Nice. All right, so why  don't we give this a little refresh here and
  4315. 5:42:33see if our data is still in. Beautiful. So we have  this. The thing is we don't have any tokens. So we
  4316. 5:42:40do have to ask ourselves how many credits. So free  plan. Okay, so we can do five I guess in total,
  4317. 5:42:44right? So maybe we'll go new syndication up top  here. We can create content. But notice how we
  4318. 5:42:50don't have LinkedIn or Twitter. So, one more  change I'm going to make is under Oh, actually,
  4319. 5:42:55I guess that's to be expected because I selected  LinkedIn and then that one X or Twitter does not
  4320. 5:42:59have an API and then blog is manual. When I click  new syndication, there's currently only LinkedIn
  4321. 5:43:05X/ Twitter and blog available. I'd like you to  add all. We also need to force the user to connect
  4322. 5:43:10at minimum LinkedIn and we need to do this post  onboarding. To be clear, are we giving them five
  4323. 5:43:15free credits as in five free generations? Another  thing on LinkedIn is now that my app is live,
  4324. 5:43:20we actually need to change the URL. So rather than  being localhost 3000, which is what it was before,
  4325. 5:43:26we actually have to go back to Splinter and then  type in this, not that, this. So that should now
  4326. 5:43:34give us the right redirect URI, which now if  I click on this, this will take us back here,
  4327. 5:43:39which is good. So, I'm going to paste in this  password, click sign in, see if I have to
  4328. 5:43:47connect via this. Okay, no, and I don't. That's  great. I'll head over to dashboard here. Now, we
  4329. 5:43:52have one active platform configured. And um what  else we should do is we should offer some sort of
  4330. 5:43:57like notification saying, hey, connect an active  platform. If a user has zero apps configured, then
  4331. 5:44:03encourage them to connect to platform. Um, drip  this out in various places throughout the app.
  4332. 5:44:10Okay, I'm going to add that here. And then I'm  just going to paste this in, then click generate.
  4333. 5:44:16So now I'm actually going to run through and  I want to see how this interacts with credits,
  4334. 5:44:20right? We're not doing payments here. We're  just doing um credits. It's your consumption.
  4335. 5:44:32Cool. This looks pretty solid. Okay, nice. So I  can do that. Let's check and see whether or not
  4336. 5:44:37this is actually going to work by heading back  to my page. And then I'll also check my posts.
  4337. 5:44:44Then if I can make the post, uh I'm just not  going to test it again. I'm just going to assume
  4338. 5:44:48that this is going to work. Okay, it's saying  published. Refresh. Okay, cool. So, I'm going to
  4339. 5:44:56now delete this. That's pretty great. Uh posting  functionality, which is the core functionality,
  4340. 5:45:01clearly works well. Okay, going back to  the dashboard, we now have one generation,
  4341. 5:45:06but no tokens have been consumed. So, we're going  to have to fix that as well. I'm not seeing any
  4342. 5:45:11credit consumption. I just submitted a request as  a Okay, cool. So, credit consumption here hasn't
  4343. 5:45:17been fixed, but I do have this, which is nice.  So, I have the whole post. That's lovely. Let's
  4344. 5:45:22um see if we can create a voice profile now. Okay.  And then we can also adjust the system prompt,
  4345. 5:45:27which is nice. Cool. Looks like there's a uh  default system prompt here. And then there's
  4346. 5:45:31also the ability to add writing examples. Nice. I  really, really like this design. It's super clean.
  4347. 5:45:36Very brutalist, which is nice. As you can see,  we have one data point. Um, it's picking up our
  4348. 5:45:40time. So, 12:57 p.m. we submitted one, which is  really cool. And then it looks like we've outputed
  4349. 5:45:46one LinkedIn post, but it's also writing one  Xthread. Also, I only published this to LinkedIn,
  4350. 5:45:52but it's telling me that I've also published  an X thread. Perhaps we should just add more
  4351. 5:45:56context surrounding output types in analytics  so that they know that you have the option to
  4352. 5:46:01copy from Xthread whereas the LinkedIn post  was actually published. Okay, heading down to
  4353. 5:46:06scheduling here we could see a content Q. So  this is the generation I can actually select
  4354. 5:46:11uh something I have generated which is neat.  So maybe instead of like publishing what you do
  4355. 5:46:16is you just generate a bunch of things. You then  select the specific platform you want. So in our
  4356. 5:46:20case LinkedIn then you can set the date using this  cute little calendar. So, why don't I pretend it's
  4357. 5:46:262025 0228? Okay. And then I don't know, we'll  do 255 in the morning. That looks good. Let's
  4358. 5:46:34add to Q. Cool. And so, now we do have something  coming up on Saturday at 255, which is nice. Now,
  4359. 5:46:42moving over here to setup. It looks like I can  change my account details here. Let's just pretend
  4360. 5:46:49I'm only saving my name. If I refresh this, you  see that that does not persistent. The setup page
  4361. 5:46:55doesn't save my account details when I change it.  For instance, I changed my name from Nikki Sariah
  4362. 5:47:00to Nikki Wiki. I press save changes and then  refresh the page and there was no um context
  4363. 5:47:05there. I do like how under billing we do have uh  both the free plan and then we have starter, pro,
  4364. 5:47:10and business. So, that's nice. Then we have  these little notifications and it looks like
  4365. 5:47:13they're toggling fine, which is good. I do wonder  I don't think that this is 100% hooked up. So,
  4366. 5:47:18we'll have to double check that. We have the  ability to delete an account. Oh, wow. Okay.
  4367. 5:47:22Okay. And that autodeletes. So, we need to set  some sort of like feature that basically checks.
  4368. 5:47:28I just clicked delete account and it immediately  signed me out. Make sure that there's some sort
  4369. 5:47:32of are you sure message. Okay, that looks pretty  nice. Okay, now I guess this is good for me. If
  4370. 5:47:40this actually did delete my account. Okay, no,  it didn't actually delete my account. I see. So,
  4371. 5:47:45it just said that it deleted my account, which  is unnecessary. Never mind. It just said that
  4372. 5:47:49it deleted my account. It didn't actually do the  deletion. Okay, now I'll generate new key example
  4373. 5:47:56key. Okay, and then we need the curl details.  I'm just going to see if we could key here.
  4374. 5:48:10Let's reveal this. And I'll say API key  send a request to this URL using the format.
  4375. 5:48:21Let me see if it makes any sense whatsoever.  API splinter.io. Okay, for the API request, it
  4376. 5:48:28doesn't look like the domain is a live host. Um,  update everything so that it reflects the new URL,
  4377. 5:48:35not api.splinter.io. And then finally, we have  this web hook feature, which uh I don't know,
  4378. 5:48:41let's just go web hook test. And over  here, we can copy a web hook URL. We
  4379. 5:48:47could basically paste that into our app and say,  "Hey, when this is complete, scheduled or posted,
  4380. 5:48:52I want you to deliver to this." So then I'm going  to go back to content library. And then I'm just
  4381. 5:48:56going to do one more. So I guess we'll go to  dashboard, new syndication here. Then I'll just
  4382. 5:49:02copy all of this over again. Paste it in. Okay.  And we have all the rest of these buttons now,
  4383. 5:49:07which is wonderful. Click generate. And then I'm  going to go here and then check to see whether or
  4384. 5:49:13not a web hook was actually sent. If the web hook  wasn't sent, I don't believe it will be. I'm just
  4385. 5:49:17going to notify the agent. Hey, the generation  occurred, but the web hook was not sent to the
  4386. 5:49:21address that I added. Um, double check that all  of that is okay. I imagine there's probably some
  4387. 5:49:25issue related to the fact that we're not on the  URL that we initially thought we'd be on. Yeah,
  4388. 5:49:32cool. So, we have that the generation has  occurred. We didn't end up getting that.
  4389. 5:49:36I can copy this, though. Go back to dashboard.  Now, I see we have two created. And there's the
  4390. 5:49:41content library here with the the the second  post, which is nice. Okay, what else is it
  4391. 5:49:45telling me? It's telling me that um all the code  examples have been updated. So, I should be able
  4392. 5:49:51to go back to API access here and then give this a  little refresh. I'm giving this a refresh because
  4393. 5:49:58I wanted to hardcode the change. Okay, just  taking a look at this code. Example still says
  4394. 5:51:02Okay, I'm going to go to upgrade and let's see  if that works. So, we can now select one of these
  4395. 5:51:06three options. So, I'm going to go pro. Seeing  that it's opening up a Stripe checkout page,
  4396. 5:51:11which is good. I'll go to USD and then I'm  just going to pretend enter some details
  4397. 5:51:14here and then click subscribe. Looks like the  processing is occurring, but is it going through?
  4398. 5:51:20Okay, cool. So, it looks like it went through.  Did we go back to checkout? Okay, cool. Yeah,
  4399. 5:51:24we have and we've upgraded. When a user pays, um,  add some confetti or something upon the redirect
  4400. 5:51:30only when they make it back after paying. Okay,  after a little bit more back and forth, you can
  4401. 5:51:34see we actually have the right profile set up. So,  I'm going to head back to Stripe, generate a new
  4402. 5:51:38key, and then actually reveal and then copy this  whole key. And I'm just going to see if this ends
  4403. 5:51:44up working because that's the API functionality.  Okay, we're still getting unauthorized. Um, this
  4404. 5:51:53using this superb basease session. I don't know  exactly what that is. I imagine this is probably
  4405. 5:52:00going to solve it. Yeah. Okay. So, we we're going  to have to rewrite that a little bit. The good
  4406. 5:52:04news is the name now saves along with various  password problems. Uh, we've now solved all of
  4407. 5:52:09that. Wonder what managed subscription is going  to look like. I've never been there before. Oh,
  4408. 5:52:13nice. Okay, cool. So we can actually like we we  literally have like our own managed subscription
  4409. 5:52:16page which is Sweet. Um why don't I go to  dashboard just so I could take a look at that as
  4410. 5:52:20well. Cool. So here are the generations and stuff  like that. Nothing upcoming because I don't think
  4411. 5:52:24we have anything scheduled. Yep. Cool. Yeah. All  right. This looks pretty good. Generated formats.
  4412. 5:52:28LinkedIn post two generated exert one generated  formats generated. Cool. Cool. This tells me what
  4413. 5:52:34they are now. And then we have access to all of  our old posts. Awesome. So now I'm just going to
  4414. 5:52:39mobile optimize this and then run security audit.  And then honestly that's it. We're live, baby. We
  4415. 5:52:44can see we're actually sending over a live API  request to the Splinter-app API as well. So,
  4416. 5:52:49this isn't just a front-end app for us anymore.  This is entirely um yeah, this is super clean.
  4417. 5:52:54Super clean. So, yeah, pretty stoked about that.  We also have the API functionality. Obviously,
  4418. 5:52:58we could paste in links as you guys have seen.  Not going to lie, this is pretty solid as far
  4419. 5:53:02as apps go. We uh now basically have something  that's capable of doing everything that I want.
  4420. 5:53:06Last thing is I'm just going to paste in this  security prompt. And just because we've done
  4421. 5:53:09this what three times now, I'm not going to bore  you all with the details, but suffice to say,
  4422. 5:53:13using Gemini 3.1 Pro in conjunction with Claude  Code for both a mixture of front-end design and
  4423. 5:53:19then backend configuration, route creation,  and then payments, and so on and so forth,
  4424. 5:53:23is pretty dang efficient. Now, I should note  that we used a ton of tokens this time, and I
  4425. 5:53:27don't actually recommend using that many tokens,  like committing that many tokens to an app. Um,
  4426. 5:53:32I just did this because I traded off speed uh  basically for money. I wanted to get this done
  4427. 5:53:37as quickly as humanly possible because of an  upcoming engagement, not necessarily, you know,
  4428. 5:53:41have three or four instances of cloud running  or uh, you know, take three or four hours when
  4429. 5:53:45realistically I could have done it in 45 minutes.  So, I'm not going to push the fast mode on you.
  4430. 5:53:49It's just an option. Uh, just keep in mind it does  cost a fair amount. This session was probably at
  4431. 5:53:53least $70. And I'm sure you can imagine if  you develop an app every couple of days or
  4432. 5:53:57work on your codebase every few days, that sort  of thing is going to add up pretty quick. For me,
  4433. 5:54:01I'm happy to do it because of the arbitrage and  then the value that I got to produce. Hopefully
  4434. 5:54:05you guys now see how to build an app just like  this. Not just a simple CRUD app, but a CRUD app
  4435. 5:54:09that also has API wrapping functionality that does  OOTH integration with social media platforms even,
  4436. 5:54:14which are some of the most secure and difficult  to authenticate and organize. And then finally,
  4437. 5:54:20um, payment integrations as well, like with  Stripe. All right, so you now know how to
  4438. 5:54:25vibe code an app. Congratulations. However, most  people that have gotten to this point are probably
  4439. 5:54:31not just interested in building internal apps and  tools for themselves. Like, if you've gotten to
  4440. 5:54:35this point, you're probably really interested in  building for other people, whether it's consumers,
  4441. 5:54:40whether it's other businesses, maybe it's some  organizations that you're working with or whatever
  4442. 5:54:43you want to help economize their workflow and so  on and so forth. And so, what I wanted to do next
  4443. 5:54:48is round out the course with a module all about  pricing, packaging, and selling what you build.
  4444. 5:54:54Now, most people that are here in your shoes,  okay, that are probably interested in um pricing,
  4445. 5:55:02packaging, and selling what they just put  together, don't really have any experience doing
  4446. 5:55:06so. And so, it's not that they don't have any like  vibe coding um business experience. It's that they
  4447. 5:55:11don't have any business experience in general. And  so, what I wanted to do is just give you a very
  4448. 5:55:14highle look at some tactics and playbooks that  you could follow to significantly streamline your
  4449. 5:55:20ability to actually successfully go out there and  then sell this sort of stuff. whether you know at
  4450. 5:55:24a small scale or whether at a large scale, whether  your goal is to replace your income or whether
  4451. 5:55:28your goal is to, I don't know, start a business  that does $100 million. Now, I think there are
  4452. 5:55:32a lot of people on YouTube that make courses on  vibe coding and stuff and um they're like, "Oh,
  4453. 5:55:37you know, here's how you make all these super cool  crazy apps and here's how I spun up 500 clones and
  4454. 5:55:42publish them to the app store." But not a lot of  these people have actually made money. So, I know
  4455. 5:55:45that this is a vibe coding course, but hopefully  it'll allow me to dive a little bit into the
  4456. 5:55:49business side of things because personally, that's  what I find the most interesting. Collectively,
  4457. 5:55:52my businesses make over $300,000 a month in  profit. Um, and that's a pretty easy number to
  4458. 5:55:56hit revenue-wise, I think, if you know what you're  doing. But profit-wise is a different story. So,
  4459. 5:56:00all this to say, you know, I I do this sort of  thing professionally. I generate revenue outcomes
  4460. 5:56:04and profit outcomes professionally for businesses  at this point. Let me run you guys through at
  4461. 5:56:08least at a high level what I know and what you  guys can use to make some money with vibe coding.
  4462. 5:56:12So, the big thing I want you guys to know is over  the course of the next, you know, 5, 10, 20 years,
  4463. 5:56:17um, software will no longer be the moat. So back  in the day, right, 30, 40 years ago, if you were
  4464. 5:56:22a cool startup and you were working on some new  computer system, okay, and you were smarter than,
  4465. 5:56:28you know, your competitors and you spent more time  on it than competitors, you might have had like
  4466. 5:56:32a small edge and maybe with that small edge, you  would have carved out like an operating system or
  4467. 5:56:37something like that. And maybe potentially you  would have called that Windows OS and then you
  4468. 5:56:42would have sold that at scale to people and that's  how you would have made your money. So if you
  4469. 5:56:45think about it like Microsoft and Windows, Windows  uh uh was like software mode, software as a mode.
  4470. 5:56:51Same thing with like the Apple brand of computers.  Same thing with like I don't know applications
  4471. 5:56:55afterwards like Photoshop and like various  databases and stuff like that. Businesses that
  4472. 5:57:00were built entirely off of software made sense  like 30 or 40 years ago because software back then
  4473. 5:57:05was very difficult to make. Okay. Well, nowadays  software is very easy to make as hopefully I've
  4474. 5:57:10just demonstrated here over the course of the  last six or seven hours or however long this
  4475. 5:57:13damn course ended up being. So, we've transitioned  pretty heavily. Unfortunately, a lot of people are
  4476. 5:57:18still stuck in that old school world where they  think, okay, that they're going to put together
  4477. 5:57:22this incredible software solution that nobody else  in the market can do because they're smart and
  4478. 5:57:27they're intelligent and they're they're visionary,  they're a forward thinker. The probability that
  4479. 5:57:31you do that is extremely low. It's extremely low.  Not just because, you know, nobody's as special as
  4480. 5:57:36we think we are, but uh because there are soon to  be 100 million times as many software engineers in
  4481. 5:57:44the form of AI agents than there ever would have  been human beings. And so moes are no longer made
  4482. 5:57:51through software. Your edge in the market is no  longer in the cool algorithm that you come up with
  4483. 5:57:56or whatever the heck. Okay. where the moat is is  in distribution, which is fundamentally different.
  4484. 5:58:05And rather than play by the software mode playbook  like everybody in their mom is doing right now,
  4485. 5:58:10um I encourage you to play by the distribution  mode playbook. Hypothetically, why do you
  4486. 5:58:15think Netflix is still Netflix in a world where  literally anybody could just tell their agent,
  4487. 5:58:21hey, here's Netflix.com. can you go and recreate  everything about it and then I don't know you
  4488. 5:58:26know host the the servers and set up databases  and set up all the infrastructure and then like
  4489. 5:58:31have a little login page everything like that the  reason why Netflix is not broke you know today is
  4490. 5:58:37because Netflix contains within it distribution  it contains a collection of clients vendors
  4491. 5:58:45relationships their staff their team their culture  and so on and so on and so forth and these are
  4492. 5:58:51things that an AI agent and until they, you know,  hook it up to the cloning vats and start pumping
  4493. 5:58:56out clients, vendors and and staff members, um,  cannot currently do or reproduce. And so software,
  4494. 5:59:05which used to be like the golden goose, right,  has basically been replaced almost completely
  4495. 5:59:12with distribution. Okay? And in a world where  anybody could build any software, the only thing
  4496. 5:59:18that makes your software different from somebody  else's software are the customers essentially the
  4497. 5:59:23vendors, the relationships, and the staff on  your team um that manage it. Anybody in 2026,
  4498. 5:59:292027 and beyond with a couple of ideas, a high  degree of agency, which just means your ability to
  4499. 5:59:35like enact your will on the world, go out and do  things, and a very small budget, just a few bucks,
  4500. 5:59:39literally 15, 20 bucks, can now build whatever  the heck they want. the whole moat, the whole
  4501. 5:59:44edge is just your ability to actually reach and  then retain people within an ecosystem. And if you
  4502. 5:59:48can do that, right, and if you can focus your time  and energy accordingly, then you can make a lot
  4503. 5:59:53of money. But if you're stuck in the software  days, then you're just spinning your tires,
  4504. 5:59:56man. The whole world's up and moved on and you  don't even know it yet. Hypothetically speaking,
  4505. 6:00:00I want to pretend right now that um you know,  we we we got a little clock here, and this is a
  4506. 6:00:05terrible drawing of a clock, but you know, bear  with me. Just pretend that this whole thing is,
  4507. 6:00:10you know, a 60-second um um hand. Imagine that the  entire life cycle of this vibe coded business that
  4508. 6:00:17you are about to start is this hand. Okay? And it  traverses a whole 60-second length. Here is how
  4509. 6:00:23much I'd recommend that you actually spend on the  vibe coding part. Okay? Over the full 60-second
  4510. 6:00:30life of your business, I would recommend you spend  maybe 3 or 4 seconds on the actual building. Let
  4511. 6:00:39me make this a little smaller so we can see it  better. Everything else, okay, literally the
  4512. 6:00:46rest of all of your time, my recommendation would  be to spend it not on building, not on tweaking,
  4513. 6:00:53not on making your server infrastructure better,  not on doing whatever the hell. My recommendation
  4514. 6:00:58would be to spend it on marketing. And this isn't  a joke. If you spend 3 seconds or 12th or 5% on
  4515. 6:01:08building, you should spend the other 1920ths or  95% on the marketing. I don't know if you guys
  4516. 6:01:18have been in like the the build and public space  on X. I used to be uh uh you know following that
  4517. 6:01:23fairly frequently because it was just interesting  to me how people would share their revenues and
  4518. 6:01:26talk about the apps they were building. And back  then they said you should spend at least as much
  4519. 6:01:29time building as you spend marketing. You should  spend at least as much time marketing as you do
  4520. 6:01:33building. And I was like okay so 50/50. Um that  was like four or five years ago. That no longer
  4521. 6:01:38applies. You need to spend like 19 to 20 times  as much time marketing than building cuz anybody
  4522. 6:01:43could do the building. The building is literally  just like your entry ticket to get onto the ride.
  4523. 6:01:48The whole ride itself is your poorly spelled  marketing. So without marketing and sales,
  4524. 6:01:54to be clear, you have no product. You may think  you have a product, but it's not a product. It's
  4525. 6:01:59just a hobby because without customers, you  don't have any sort of business. You need
  4526. 6:02:04revenue and so on and so forth. There are also  some additional benefits to having um customers
  4527. 6:02:09that go far beyond the money that they pay you.  If you have customers, what you get is you get
  4528. 6:02:14faster iteration because you're listening now to  real market feedback. You're not listening to like
  4529. 6:02:19your own opinions and your assumptions, which is  what most builders will do. Most builders are like
  4530. 6:02:24heavily biased. I mean, who the hell builds  software products anyway? For the most part,
  4531. 6:02:27giant nerds, okay? Myself included. I don't know  what the average human being that uses my product
  4532. 6:02:32actually wants or thinks. So, everything that I'm  doing is just assuming. I'm using my own opinions
  4533. 6:02:38essentially and I'm hoping that my opinions  are correct because I possess a strong level
  4534. 6:02:41of empathy or whatever the hell. But the reality  is most of the time I'm wrong. You know, it's like
  4535. 6:02:46a ven diagram. You know, maybe like if this is  my opinions, maybe only like 50% of my oh my god,
  4536. 6:02:53I really need to I'm writing like a doctor.  Um only like 50% of my opinions are actual
  4537. 6:03:00reality. And so the only part of like this ven  diagram that I'm actually moving the needle for
  4538. 6:03:05and like building features into my app that  actually make sense, okay, are over here. But
  4539. 6:03:09like the other 90% is all [ __ ] you know? It's  all like uh I'm just wrong. So why would you even
  4540. 6:03:14like worry about your opinions? Instead, focus off  reality and ground truth. The only way you can get
  4541. 6:03:21reality and ground truth is getting customers.  The ideal is sufficient number of customers.
  4542. 6:03:26so many so that you could start averaging  out their opinions and beliefs and desires
  4543. 6:03:29and needs and so on and so forth and then you  just start designing for them. So rather than
  4544. 6:03:33letting your own assumptions build the product,  use customer requirements, use customer needs and
  4545. 6:03:37actually do like customer surveys. Launch your  vibecoded app today. You know, hypothetically,
  4546. 6:03:43you've seen how easy it is to do. You know,  I can build one of these in just an hour or
  4547. 6:03:46two. Okay? And then contact 20 people and have all  of them use your app for free and then tell you,
  4548. 6:03:51hey, I liked this. I didn't like that. Hey, I  thought this could have been better. Hey, this
  4549. 6:03:54didn't really solve my need. Hey, I wish it did  this. I wish it did that. Take all that feedback
  4550. 6:03:58and then use it to design the next version of  your app because it's not the first version of
  4551. 6:04:01your app that's going to make you any money. It's  like the 20th version of your app that's going to
  4552. 6:04:04make you money. In addition, because customers and  distribution is really the moat, your whole focus
  4553. 6:04:09should be on maximizing the customer experience at  every step. It should not be on making the nicest,
  4554. 6:04:14sexiest, most polished app. And I know this is  kind of annoying cuz I did just spend the last
  4555. 6:04:18part of, you know, five or six hours hopefully  teaching you guys how to do this and how to like
  4556. 6:04:22make a really good product. But in reality, the  product, as we've seen, is really only like 5% of
  4557. 6:04:27the whole pie now. So, focus instead on acquiring  as much distribution as quickly as possible. I'm
  4558. 6:04:32going to run through some specific ways on how to  do that. And then once you have that distribution,
  4559. 6:04:36um try and satisfy the needs of your customer.  And then generally and consistently iterate on
  4560. 6:04:40the product. Okay. So, highle advice aside,  how do you actually do the big thing that I
  4561. 6:04:46think a lot of people are wondering? How do you  price your product? Well, what I want to do next
  4562. 6:04:52is talk about essentially my core principle for  pricing. And this is a core principle that I've
  4563. 6:04:56used to generate tens of millions of dollars in  revenue across a variety of businesses, small
  4564. 6:05:00to mid-size businesses, my own agencies, digital  marketing businesses, uh a couple multi-billion
  4565. 6:05:05dollar portfolio companies. And um this is  something that I just I I continuously return
  4566. 6:05:09to you because it's the easiest and simplest  way to price. So, it's called VBP or valuebased
  4567. 6:05:18pricing. And so in value based pricing, what  you do is you price based off the value that
  4568. 6:05:23your app delivers, not on your costs or your  competitor's pricing. You know, and I think a
  4569. 6:05:28lot of people are like, well, I have to anchor to  my competitor's price, don't I? And to me, I say
  4570. 6:05:32I mean like obviously your competitor's price is a  factor and people are going to be doing some price
  4571. 6:05:36shopping. But if you focus on the value instead of  at what your competitors price rather than running
  4572. 6:05:41uh down to the very bottom and it being like a  race down below like a lot of these freelance
  4573. 6:05:45platforms and stuff where somebody bids nine,  another bids eight, another bid seven till you're
  4574. 6:05:49at freaking zero. What we do is we just establish  how tremendously valuable a product is and then
  4575. 6:05:54charge such a vanishingly small percentage of said  value that the customers are bought in regardless.
  4576. 6:06:00I mean to them it's like a it's it's a pittance.  And I know this because I also purchase software.
  4577. 6:06:04um what ultimately a lot of B2B software users  are looking for is something that maximizes their
  4578. 6:06:09return on investment and minimizes the friction  involved in making the purchase decision. So let
  4579. 6:06:13me explain what I mean by all this. There are two  types of value that you can produce at least in a
  4580. 6:06:17B2B environment. In a B2C environment you have  additional types of value. Those types of value
  4581. 6:06:21are nonmaterial and so it will not be discussed.  You have the ability to directly reduce their
  4582. 6:06:27expenses which is the money that your product  will save a customer if they use you. And then
  4583. 6:06:32you also have the ability to significantly  increase their revenue in opportunity cost,
  4584. 6:06:38which is also termed the additional money  customers can now earn because they use your
  4585. 6:06:42product. I think direct expense savings are pretty  simple, right? If I have product X and product X
  4586. 6:06:48currently costs the user $100 a month and I say,  hey, I just built product Y. Product Y only costs
  4587. 6:06:55$5 a month. What do we have there? What I've done  is, if you think about it, I've saved the customer
  4588. 6:07:01$95 every month. And so the direct expense savings  are 95 bucks. Easy. Now, an opportunity cost. Now,
  4589. 6:07:12opportunity cost is a little bit different.  Instead of focusing specifically on what the
  4590. 6:07:15delta between, you know, their old thing and then  their new thing is, what we focus on instead is
  4591. 6:07:21how much time do they save and what is the  cost of that time. So I'll give you a brief
  4592. 6:07:30little example. Let's say hypothetically you  are currently a salesperson. You work at big
  4593. 6:07:36company. Big company pays you on average about  $100 per hour. Right now, as part of your day,
  4594. 6:07:44you do some [ __ ] admin task. That admin task  involves filling out some CRM or whatever. And
  4595. 6:07:50on average, every single day, you have to spend  2 hours doing this. Okay? So, they're paying you
  4596. 6:07:57$100 an hour. You're doing an admin task that is  worth 2 hours. If you hypothetically could build a
  4597. 6:08:03software solution that enable this salesperson  to spend zero minutes doing this admin task,
  4598. 6:08:08how much money are you saving this salesperson  right off the bat? You're saving this company
  4599. 6:08:13right off the bat. You're saving $2* $100 an hour  or $200 an hour. That is your direct expense. But
  4600. 6:08:23if you think about it, what do sales people do?  Salespeople are tasked with increasing the revenue
  4601. 6:08:29of the business that they work in. Hypothetically,  let's say if instead of focusing on admin time,
  4602. 6:08:36they then focus on sales, aka calling people or  whatever. in those two hours they could contact
  4603. 6:08:4250 people and if in one in 50 people end up  purchasing a small product or something like
  4604. 6:08:48that okay which is their conversion rate and if  the average cost of that product is let's say
  4605. 6:08:53uh I don't know $500 then by saving 2 hours a day  not only are you adding $200 sorry $200 an hour
  4606. 6:09:03I meant $200 not only you adding $200 back to the  core business that you built the software platform
  4607. 6:09:08for you're also adding If you think about it,  an additional $500 in revenue. So this is minus
  4608. 6:09:15$200 of expense. Okay? And this is plus $500  in revenue. And if you think about the total
  4609. 6:09:25amount now that this software product is saving  or generating the business, we have come to
  4610. 6:09:32$700 in value and that's per day. Okay. So the  expense portion is about saving money whereas
  4611. 6:09:40the revenue portion is about reallocating the time  that your software solution is now saved to allow
  4612. 6:09:45a person at a business to focus on higher revenue  things that actually produce for a company. And in
  4613. 6:09:51practice usually these expenses are much smaller  than the total amount of opportunity cost aka
  4614. 6:09:56the revenue that you are unlocking. So you know  how earlier we built a thumbnail generator? Well
  4615. 6:10:00here's a quick example of what that might look  like. You have direct cost savings. Let's say
  4616. 6:10:05right now whatever system that they are using  cost them $50 a thumbnail and they generate 20
  4617. 6:10:10thumbnails a month. That means that by switching  over to nyx thumbnail company.co, also known as
  4618. 6:10:16thumbly, uh you'll save $1,000 a month. But when  you take into account the time savings revenue,
  4619. 6:10:22okay, you move this 2 hours per thumbnail design  period to 5 minutes. What you're doing is you're
  4620. 6:10:28saving 115 minutes. And hypothetically, let's  say these 115 minutes times 20 are 2,300 minutes
  4621. 6:10:36a month. Let's say with this additional time,  which works out to be approximately 40 hours,
  4622. 6:10:42this designer or something can actually make  an additional $1,000 a month as well. Well,
  4623. 6:10:46now the total value created is $2,000 a month.  What we're doing as somebody that is developing
  4624. 6:10:51a thumbnail product is we're pricing at a very  small percentage of the total value we produce,
  4625. 6:10:55so maybe 10%. So, we charge 200 bucks a month. And  then the customer ends up making 10 times as much
  4626. 6:11:00money as they spend with us for using our service.  Now, obviously, this is going to be an average,
  4627. 6:11:04right? Every customer is going to be different.  Some people are going to produce way more value
  4628. 6:11:08than your $2,000 a month estimate. Others are  going to produce less value. But because you
  4629. 6:11:12can't price individually per every new customer  that you onboard, you have to pick a specific
  4630. 6:11:16package price. What we've done now is we've  basically used facts and logic to work out what
  4631. 6:11:21a strong value would be for a core product and  then how much to charge for it instead of relying
  4632. 6:11:27on things like competitor analysis or worrying  about what the dude in the next cubicle over is
  4633. 6:11:32doing. And so this is a much more sustainable and  higher ROI way of pricing. You're pricing based
  4634. 6:11:36off value. You're not pricing based off of what  everybody else is doing. This young viewers is
  4635. 6:11:41how you zigg when everybody else zags. Once you've  established some sort of price for your product,
  4636. 6:11:46my recommendation is I actually establish  this as my top price. So, for instance,
  4637. 6:11:51um let's say I kind of screwed up the uh writing  here, but let's say this is like your top tier,
  4638. 6:11:56this is your mid tier, and this is your entry  tier. You know how there's typically multiple
  4639. 6:12:00subscription tiers for a product, right? Assuming  you're doing a monthly thing. What you do is you
  4640. 6:12:03take the top and then you set that one at uh you  know, let's say 200 bucks a month. And what you
  4641. 6:12:08do is you set your middle at approximately half of  that and you set that at about 100 bucks a month.
  4642. 6:12:13but you uh reduce the ROI to compensate. So in  this case, you know, previously I'm offering a
  4643. 6:12:1710x ROI on my top. Well, now I'm offering an 8x  ROI on my mid and then a 6x ROI on my entry. And
  4644. 6:12:23so in this way, you have like a reasonable product  differentiation. You have a reasonable spread of
  4645. 6:12:26values. And this is enough to get you started  before, you know, you can get enough customers,
  4646. 6:12:30you can actually run like strong analytics to  determine whether or not people would actually
  4647. 6:12:34prefer a $37 a month product or a $58 a month  product or whatever. And that's honestly all there
  4648. 6:12:39is to it. To make a long story short, what I do  anytime I'm pricing an app, uh, Pel, an automation
  4649. 6:12:44service, a back-end tool, even like a big business  deal, back when I was um, operating a content
  4650. 6:12:48writing agency and we were trying to work out how  much to price our product, uh, we do it all based
  4651. 6:12:52off of value pricing, which is determining how  much value our product has to the user to begin
  4652. 6:12:57with, an expense, an opportunity cost, and then  just charging a small percentage of that. And
  4653. 6:13:01that usually ends up being somewhere between 10 to  20% of the total ROI. And as a business owner, I'm
  4654. 6:13:06thinking like, hey, I could put my money in the  S&P 500, I could make 8% a year, or I could give
  4655. 6:13:10my money to NYX Co. and then I'd make a,000% on my  initial investment. What am I going to do with my
  4656. 6:13:16money when presented that choice? Obviously, I'm  going to give it to Nyx Co. right now. Uh, whether
  4657. 6:13:20or not somebody chooses to invest in you isn't  just a product of this math. It's also how much
  4658. 6:13:24they believe the math, and that's another part of  marketing. But I'll leave that for another day.
  4659. 6:13:28Hopefully, at least now you guys understand how to  price set products. But that takes us to the next
  4660. 6:13:33big thing, okay? which is well there's pricing the  product but how do I actually get my product out
  4661. 6:13:38there okay how do I actually market this amazing  thing that I have developed well there are three
  4662. 6:13:45major ways the first is outbound a lot of people  shy away from outbound but outbound was the very
  4663. 6:13:50first thing that I did when I started my first  business my first real business about 10 years ago
  4664. 6:13:54I went door to door literally knocking on business  doors coming in trying to shake their hands and
  4665. 6:13:59then sell them on my little marketing package it's  very difficult but this is ultimately what works
  4666. 6:14:04So in this case, you go directly to people who  need your product. You can consider this like a
  4667. 6:14:08sniper rifle approach. The two most popular  methods right now are cold email, which is
  4668. 6:14:12where you actually craft an email, usually using a  template that appears to be personalized onetoone
  4669. 6:14:18communication between you and the person that's  reading. And then you say, "Hey Pete, I love what
  4670. 6:14:22you're doing over at XYZ Business. I think right  now you guys are currently spending all this money
  4671. 6:14:26on the software, and I can save that for you with  XYZ product. I would be happy to give this to you
  4672. 6:14:31for like a major discount because you're going to  be one of my first five uh you know signups. I've
  4673. 6:14:35also attached a video here that runs through how  to do X Y and Z. Um let me know if you have any
  4674. 6:14:39questions. If I can help you out at all would be  happy to. Okay. And so in this way you're reaching
  4675. 6:14:43out directly to them. This is you. This is them  and this is you bridging that gap. That's why it's
  4676. 6:14:50called outbound. The other main way to do this  is through cold DMs. And typically you do this
  4677. 6:14:54on B2B platforms like LinkedIn. Cold DMs stands  for direct messages. It's just the same thing
  4678. 6:14:59as cold email. It's just instead of using like an  email inbox, which tends to be the the highway to
  4679. 6:15:04the soul, um we're instead using like a LinkedIn  message box or like an Instagram message box,
  4680. 6:15:08but it's the exact same idea. Some caveats here.  This works really well for B2B products, but it is
  4681. 6:15:14pretty difficult for consumer products, aka B2C  products, since most of the lead sources where
  4682. 6:15:19you're going to scrape this information do tend to  be B2B. Like for instance, if you think about it,
  4683. 6:15:23LinkedIn is entirely a commercial platform. If  you sign up to LinkedIn, odds are you're signing
  4684. 6:15:27up for employment or business purposes. So, you  can feel pretty safe that most of the people that
  4685. 6:15:31you're scraping on LinkedIn, you're doing so  because it is a B2B sort of transaction. Hey,
  4686. 6:15:35I can help you at XC Corp. Hey, I saw you're  employed at whatever position. I think I can
  4687. 6:15:38assist you with that and so on and so forth. If  they're not on LinkedIn, crap gets a lot harder,
  4688. 6:15:43right? So, for the most part, anytime I sell B2B,  I start with Outbound. The other big benefit to
  4689. 6:15:47outbound is it's just really fast. It is way  faster than any of the other methods on the
  4690. 6:15:50list. It's also way harder, right? you sort of  have to put your freaking ego on the line. And
  4691. 6:15:55um I can't tell you how many times I got thrown  out of businesses when I was knocking on doors.
  4692. 6:15:59Security racing after me being like, "Get  the hell out of this plaza." Uh but you know,
  4693. 6:16:03it it worked and it was what enabled me to make  my first uh probably $15 $200,000. That said,
  4694. 6:16:07this is not the only thing that you can do. It is  not the only way. There are a variety of others.
  4695. 6:16:12The second is inbound, which I think a lot more  people here are probably familiar with. Inbound,
  4696. 6:16:17if you kind of think about it logically, is  kind of like what I'm doing right now. What
  4697. 6:16:21I'm doing is I'm creating very valuable content.  I'm building a very strong and large audience of
  4698. 6:16:26people that enjoy consuming my content. And then  what I'll do is I'll direct a small percentage of
  4699. 6:16:30you guys to some paid products so that you guys  sign up to my service or whatever. The issue with
  4700. 6:16:34inbound, despite the fact that, you know, if I'm  here and then they're here, despite the fact that
  4701. 6:16:40they're now coming to you, is it's a lot slower.  It takes a lot longer to build. Okay. And what a
  4702. 6:16:46lot of people don't realize is they'll watch some  vibecoded course or whatever and then be like,
  4703. 6:16:50I'm going to make my own app business. It's going  to be awesome. And then they start making content
  4704. 6:16:53on it. What they don't realize is like when you  make content um on the on the wider internet like
  4705. 6:16:58on YouTube or LinkedIn or Instagram or whatever,  what you're basically doing is you're like in a
  4706. 6:17:02sea of a billion people and then you're  given a megaphone. And then you're like,
  4707. 6:17:06"Okay, I have a megaphone. This is awesome." And  then what you don't realize is every other person
  4708. 6:17:10also has a megaphone. And then the big people that  are pretty established have megaphones that are
  4709. 6:17:14way bigger than you. And then the small people  like yourself have these tiny little things that
  4710. 6:17:17barely produce any noise uh whatsoever. And so  growth on inbound is extraordinarily difficult
  4711. 6:17:23as a beginner unless you have some pre-established  success or pre-established wins. And most people
  4712. 6:17:28that are starting these sorts of things that  immediately turn to I'm going to post one thread
  4713. 6:17:31on Instagram every day for the next year. Uh  they they don't understand this. And so what
  4714. 6:17:35ends up happening with a lot of inbound is because  it takes so much longer to build and people are so
  4715. 6:17:41unprepared for this, they end up just screeching  into the void, never achieving anything. and then
  4716. 6:17:45quitting before they actually build up the amount  of momentum required to succeed. If I could graph
  4717. 6:17:50sort of like the differences between inbound  and outbound. And I love graphing stuff. So,
  4718. 6:17:54in case you've watched any of my other videos,  get ready for a freaking Nyxive graph. Basically,
  4719. 6:17:59this is the amount of time that it takes to see  any sort of win. And then this is the amount
  4720. 6:18:03of money that it takes. Okay? And I'm going to  I'm going to pretend that blue here is inbound.
  4721. 6:18:08And I'm going to pretend that orange here is  outbound. And you guys are going to see why
  4722. 6:18:11I prefer outbound in terms of the total amount  of money you could make. Um, if you use inbound,
  4723. 6:18:16okay, what happens is you start at this time step  one and then you make no money for a long time
  4724. 6:18:21and then all of a sudden your brand picks up and  then you make a ton of money. With outbound, it's
  4725. 6:18:26basically the exact opposite because every single  time you send a piece of outreach, it consumes a
  4726. 6:18:32little bit of your time. What ends up happening is  you usually have some success initially and then
  4727. 6:18:37you start tapering out or plateauing and hitting  a ceiling. And so if you think about it logically,
  4728. 6:18:42both of these have major trade-offs, right? But  with outbound, what happens is you make money much
  4729. 6:18:46much faster. You know, this might be 1 month. This  over here might be one year. And so with inbound,
  4730. 6:18:52what we've done is we've sacrificed all our  money in the first year for money after year
  4731. 6:18:55number one. And with outbound, what we've done  is we've sacrificed money after year 1 for money
  4732. 6:18:59before year 1. Um in reality things are never  fully black or white and so the recommendation
  4733. 6:19:04is usually to do some sort of blended take of both  where you know at the beginning you start mostly
  4734. 6:19:10with outbound. Okay. And then as time goes on you  shift more to inbound which allows you to generate
  4735. 6:19:16revenue quickly without also tapering out. Um that  said there are a variety of different ways you
  4736. 6:19:20could do this sort of thing. That's where business  programs like u mine maker school and so on and
  4737. 6:19:23so forth come into play. So I'll I'll leave that  with you and you guys could do whatever you want
  4738. 6:19:27strategically there. The third major way that you  could market as somebody that develops and builds
  4739. 6:19:30products is instead of trying to build your own  distribution via you know outbound like we talked
  4740. 6:19:36about earlier or inbound where people come to you.  What you do is you just take somebody else okay
  4741. 6:19:43somebody like Nick Sarif and you say yo Nick can  you market my product for me and then I'll just
  4742. 6:19:48pay you 30%. And then what happens is Nick, you  know, can use a combination of both inbound and
  4743. 6:19:54outbound methods to do that marketing for you. But  the idea is because he's already developed sort of
  4744. 6:19:59pre-existing distribution, it's way faster. And uh  you know, all you're really doing is you're paying
  4745. 6:20:04a percentage. So it's more predictable for you.  Maybe it won't necessarily be cheaper, but it's
  4746. 6:20:08probably cheaper than you initially buying a bunch  of software platforms, getting a bunch of cold
  4747. 6:20:12emails, uh getting a a beautiful studio and all  that stuff. So, the whole idea is you just partner
  4748. 6:20:17with someone who has pre-established distribution  and then you make it a win-win for them. You're
  4749. 6:20:20like, "Hey, man. This software does exactly what  the heck you really like to do. Uh, I think I can
  4750. 6:20:25really help your viewers and stuff like that as  well." And rather than you having to build a whole
  4751. 6:20:28new product from scratch, why don't you just use  my product and I'll just pay you a percentage. You
  4752. 6:20:32like my product, right? Yeah. Okay. Awesome. So,  it's a win-winwin. As mentioned, it can be inbound
  4753. 6:20:36or outbound affiliate, though. Inbound tends to be  the most popular one because it's more scalable.
  4754. 6:20:40And then yeah, you're just monetizing somebody  else's audience or work, which allows you to
  4755. 6:20:43like quickly jump cut in uh basically return for  some predictable outflow of your money. Okay, so
  4756. 6:20:50hopefully I've now showed you guys how to not only  price but also package together multiple tiers and
  4757. 6:20:55then also get started with the marketing of your  product. My recommendation to be clear is to start
  4758. 6:20:59with some form of outbound laser or sniper rifle  target specific people whose needs you are solving
  4759. 6:21:07and handling with your product. And once you have  a solid base set up, maybe 10, 20, $30,000 a month
  4760. 6:21:12in recurring revenue, then you can transition  over to maybe building a brand um um you know,
  4761. 6:21:17doing the whole megaphone analogy that in reality  tends to be the best of both worlds. Um affiliate
  4762. 6:21:22is also open to you at any level of the stack.  So whether you guys are early on, whether you
  4763. 6:21:26guys are a little later on, I do highly recommend  looking for those sorts of partnerships and then
  4764. 6:21:30finding opportunities to, you know, plant your  seed and have other people water them from here
  4765. 6:21:34on out. Obviously, I can't cover every possible  business permutation. Some people are going to do
  4766. 6:21:38like high ticket SAS style stuff where you have  to sit down and do demos. It's going to be more
  4767. 6:21:42sales. Other people are going to do low ticket  SAS stuff where basically people guide themselves
  4768. 6:21:46through their onboarding checklist and stuff. Um,  you know, that tends to be more marketing. But
  4769. 6:21:50hopefully this at least tells you guys a little  bit about where the market is going and then
  4770. 6:21:54how to practically take what I'm talking about  here to improve the quality of your guys' lives,
  4771. 6:21:58businesses, and so on and so forth. Okay, that  was a hell of a course. I had a lot of fun putting
  4772. 6:22:02all that together. If you guys have made it to the  end, y'all are real ones. I have uh one quick ask,
  4773. 6:22:07two, I suppose. The first is if you guys like this  sort of thing and you guys are curious about how
  4774. 6:22:11to monetize your own vibe coding business,  definitely check out Maker School. It's my
  4775. 6:22:15day-to-day accountability program where I actually  guarantee you your first paying customer for an
  4776. 6:22:19AI or automation business in 90 days. If you don't  get customer number one in 90 days, I I refund you
  4777. 6:22:25in full. So, it's a full 100% guarantee. Inside  of Maker School, you'll learn how to put together
  4778. 6:22:29really classy and clever offers, sort of like  the offer I'm using to get you into Maker School,
  4779. 6:22:34as well as do things like set up outbound  campaigns, uh, productize your business, and
  4780. 6:22:38then eventually scale to inbound, like I talked  about here. Additionally, I'd love it if you
  4781. 6:22:41could check out my podcast with Mr. Jack Roberts.  We both talk on AI automation. It's a blend of
  4782. 6:22:46news and then us just goofing around, showing  off our boulder shoulders. So, no pressure.
  4783. 6:22:51Do whatever the heck you want. Lastly, you'll  find everything that you need down below in the
  4784. 6:22:54project description. And then yeah, if you really  like this sort of thing, then please subscribe.
  4785. 6:22:57Helps out my channel. Comment and engage with the  video. And I'll catch all y'all on the next one.

About this transcript

This page contains the full transcript of VIBE CODING FULL COURSE: Gemini 3.1 + Antigravity (6 Hrs) by Nick Saraev, generated from the public captions YouTube serves with the video. The transcript has 86,707 words across 4,785 segments, with the original timestamps preserved so you can click any line to jump to that moment in the embedded player.

What you can do with it

Use the transcript to take notes, quote the speaker, build a study guide, generate a summary with ChatGPT or Claude via the YouTube Summary tool, or export it as a timed subtitle file with YouTube to SRT. You can also re-open it in the transcriber to choose a caption track available on the video.

Free YouTube transcript tool

YouTube2Text is a free YouTube transcript generator — no signup, no daily limit. Paste any YouTube link and get the full transcript instantly, with timestamps, click-to-jump, caption language selection, AI prompts for ChatGPT, Claude, and Gemini, and exports to TXT, SRT, VTT, or Markdown.